Intelligent process parameter optimization method for rubber banburying
By optimizing rubber mixing process parameters through an intelligent mixing AI control platform and AI process learning model, the problem of slow manual adjustment was solved, realizing automated and intelligent rubber mixing, and improving product quality and production efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU YINGGE INFORMATION TECH CO LTD
- Filing Date
- 2024-12-16
- Publication Date
- 2026-06-23
AI Technical Summary
The existing rubber mixing process requires manual adjustment, has a slow response speed, and cannot respond to fluctuations in raw materials and product performance requirements in a timely manner, resulting in low production efficiency and unstable quality.
An intelligent internal mixing AI control platform is adopted, which optimizes process parameters through AI process learning models, combines mean-shift and DQN algorithms for data cleaning and reinforcement learning, collects and optimizes internal mixing process data in real time, and uses MES, WMS and PLC systems for automated control.
It improves product quality consistency and production efficiency, reduces human interference, lowers energy consumption, increases process flexibility and diversity, and reduces the burden on process technicians.
Smart Images
Figure CN119918394B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of rubber mixing technology, specifically relating to an intelligent process parameter optimization method for rubber mixing. Background Technology
[0002] The rubber compounding process is a crucial step in rubber product manufacturing. It primarily involves uniformly mixing various compounding agents (such as fillers, vulcanizing agents, plasticizers, and antioxidants) with raw rubber to achieve the desired processing and performance characteristics. The purpose of compounding is to ensure that all components in the formulation are fully dispersed within the rubber matrix, forming a homogeneous mixture and guaranteeing that the physical properties and chemical stability of the rubber products meet requirements. The compounding process generally includes plasticizing, masterbatch processing, and final mixing. Rubber compounds that meet the technical requirements are then used in semi-finished product processes.
[0003] 80% of the raw materials required for tire manufacturing are produced in the internal mixing process, involving approximately 100 different types, and manufacturers frequently switch batches. Currently, the rubber internal mixing process involves research institutes developing production formulas, and process engineers then formulate the production process based on these formulas. Production equipment executes according to the process steps and parameters (such as time, temperature, energy, speed, and pressure) set by the process technicians. Generally, rubber discharge is performed based on a set combination of mixing time, temperature, and energy. A single process is finalized after numerous small-batch trials and adjustments until the finished product fails inspection. Due to factors such as changes in raw materials, weather, and performance requirements, process engineers need to frequently adjust process parameters, resulting in slow response times and an inability to fully address raw material fluctuations and product performance requirements. This significantly wastes human and financial resources, and product quality control cannot be guaranteed.
[0004] Therefore, it is very important to design an intelligent process parameter optimization method for rubber mixing that can automate and intelligentize the mixing process, as well as improve quality consistency and production efficiency. Summary of the Invention
[0005] The present invention aims to overcome the problems of traditional rubber mixing processes in the prior art, which require manual modification, have slow and untimely process feedback, and cannot meet the needs of production conditions. It provides an intelligent process parameter optimization method for rubber mixing that can automate and intelligentize the mixing process, as well as improve quality consistency and production efficiency.
[0006] To achieve the above-mentioned objectives, the present invention adopts the following technical solution:
[0007] A smart process parameter optimization method for rubber mixing includes the following steps:
[0008] S1 uses an intelligent refining AI management platform to obtain production data;
[0009] S2, extract training data from the production data, train the AI process learning model, and store it in the intelligent mixing AI control platform;
[0010] S3, the intelligent mixing AI control platform distributes the trained AI process learning model to the AI intelligent terminal;
[0011] S4, start the AI process calculation program and collect the data of the internal mixing process in real time. At the same time, input the collected data into the trained AI process learning model to optimize the process parameters and output the optimized internal mixing AI process.
[0012] S5, the auxiliary machine PLC terminal receives the internal mixing AI process and sends it to the internal mixer;
[0013] S6, the internal mixer performs the internal mixing AI process.
[0014] Preferably, in step S1, the production data includes mixing process data, step sequence reports, quality inspection data, raw material data, feeding data, and weather information.
[0015] Preferably, step S2 includes the following steps:
[0016] S21. Clean the production data, use the mean-shift algorithm to cluster the process parameters of different periods, and save all versions of process parameters in the intelligent mixing AI management and control platform according to the formula category.
[0017] S22, clean the production data, use the DQN algorithm for reinforcement learning, and save the AI process learning model obtained from the reinforcement learning based on the formula in the intelligent mixing AI control platform.
[0018] Preferably, step S21 includes the following steps:
[0019] S211, the collected production data is processed for outlier handling and feature extraction, and then processed into the required data format;
[0020] S212, for each formulation, apply the corresponding process parameters to the clustering process;
[0021] The clustering process is as follows:
[0022] The data points are initialized with the mean of each point, and the bandwidth parameter h is selected; for data point x, the corresponding Mean-Shift vector is represented as:
[0023]
[0024] Where N(x) is the set of data points within the bandwidth parameter h, i.e., the neighborhood of point x; x iThis represents the i-th data point; parameter K represents the kernel function, specifically a Gaussian kernel function; the magnitude and direction of the Mean-Shift vector depend on the data distribution within the neighborhood.
[0025] For each data point x, continuously move towards higher density, i.e. execute: x←x+m(x), repeat several times until convergence to a local maximum density point; if the convergence distance between adjacent data points is less than a set threshold, then the corresponding data points are merged into a cluster; the final centroid and corresponding data points are the clustering result.
[0026] S213 stores the characteristics and process parameters of multiple classes of each formula in the intelligent mixing AI control platform; the clustered process parameters are used to intelligently recommend processes based on changes in production conditions.
[0027] Preferably, step S22 includes the following steps:
[0028] S221 handles outliers and missing values in production data, specifically including missing value interpolation and imputation, data smoothing, and data standardization.
[0029] S222: Extract features from the data processed in step S221, and filter out effective feature data through statistical analysis and dimensionality reduction.
[0030] S223 divides the effective feature data into training, validation and test sets for subsequent model training and evaluation.
[0031] S224 uses the DQN algorithm for reinforcement learning, and the specific process is as follows:
[0032] Determine the state space of the internal mixing process, including process data, feed data, and mixing quality data;
[0033] Define the action space of the intensive mixing process, including rotation speed, pressure, time, temperature, and energy;
[0034] Design a reward function based on the quality requirements of intensive mixing, and design immediate rewards considering production efficiency and product quality;
[0035] Build a DQN network model, construct a simulation environment based on historical production data, use the DQN algorithm for reinforcement learning training, and gradually optimize the strategy of the DQN network model.
[0036] The trained DQN network model is stored in the intelligent AI management and control platform.
[0037] Establish a feedback mechanism to collect data on the performance of the DQN network model in actual production, evaluate the performance of the DQN network model, and retrain or fine-tune it regularly based on new production data.
[0038] Preferably, step S4 includes the following steps:
[0039] S41, during production, the AI process calculation program obtains the current production formula information and feeding information from the MES interface, obtains the corresponding raw material inspection data from the WMS system interface, obtains weather data from the intelligent mixing AI control platform, and uses the cosine similarity algorithm to calculate the AI process that best matches the current production environment.
[0040] S42, the AI computing program on the AI smart terminal writes the generated process parameters to the upper auxiliary machine PLC terminal and notifies the upper auxiliary machine PLC terminal that the process parameters have been written.
[0041] S43, after the auxiliary machine PLC terminal receives the new process parameters written by the AI process calculation program, it replaces the currently executed process parameters.
[0042] S44, the internal mixer executes the AI process to produce rubber compound. The AI process calculation program captures real-time process data through the auxiliary PLC terminal at a fixed frequency.
[0043] The AI process calculation program on the S45 AI smart terminal further optimizes the new process parameters based on real-time process data, generates the mixing AI process, and then re-issues it to the auxiliary machine PLC terminal through the AI calculation program.
[0044] Preferably, step S41 includes the following steps:
[0045] S411 obtains current production formula and feeding information from the data interface of the MES system, raw material inspection data and origin data from the data interface of the WMS system, and weather data from the intelligent mixing AI control platform.
[0046] S412, by linking formula information and feeding information with quality inspection data and raw material data, obtain the current formula material composition and material inspection data;
[0047] S413, by processing the data obtained in steps S411 and S412, the feature vector A = (a1, a2, ..., a...) of the current feeding information is obtained. n The data processing steps include data formatting, outlier handling, missing value imputation, feature extraction, numerical encoding and normalization of categorical features.
[0048] The clustering results of the current production formula from the intelligent internal refining AI control platform are retrieved. For each cluster, the corresponding feature vector B = (b1, b2, ..., b...) is extracted. n ), calculate cosine similarity:
[0049]
[0050] The process with the highest cosine similarity is selected as the one that best matches the current production environment.
[0051] Preferably, step S42 includes the following steps:
[0052] S421, the AI smart terminal runs an AI computing program to intelligently generate process parameters based on current production needs, historical data, and raw material data;
[0053] S422, encode the generated process parameters in a format that the PLC can understand;
[0054] S423 transmits the encoded process parameters to the auxiliary PLC terminal via industrial Ethernet.
[0055] S424 After the transmission is completed, the AI intelligent terminal notifies the auxiliary PLC terminal that the new process parameters have been written by updating the status of the corresponding monitoring points. After the PLC detects the status update, it issues the process parameters for execution.
[0056] Preferably, step S45 includes the following steps:
[0057] S451, after the AI process calculation program obtains complete real-time process data, it performs analysis and processing, and extracts the process curve features;
[0058] S452 calls the trained AI process learning model to further optimize the process parameters and generates an optimized mixing AI process, which is then re-sent to the auxiliary machine PLC terminal through the AI calculation program.
[0059] Preferably, step S6 includes the following steps:
[0060] S61, quality inspection of the produced rubber compound, and the inspection results are synchronized to the MES system;
[0061] S62, the intelligent mixing AI control platform collects rubber compound inspection data and process data obtained from the mixing AI process;
[0062] S63, add the newly generated data from step S62 to the existing production data, perform incremental learning, and repeat steps S1 to S5.
[0063] Compared with the prior art, the beneficial effects of this invention are: (1) the method of this invention can improve product consistency; (2) the method of this invention can improve production efficiency; (3) the method of this invention uses data model to drive decision-making and reduce human interference; (4) the method of this invention can reduce ineffective mixing time and reduce energy consumption; (5) the method of this invention can reduce the burden on process technicians and allow them to spend more time and energy on monitoring and adjusting the entire production process; (6) the method of this invention increases the flexibility and diversity of the process and provides data support for further improving the process level. Attached Figure Description
[0064] Figure 1 This is a schematic diagram of the intelligent process parameter optimization method for rubber mixing according to the present invention.
[0065] Figure 2 This is a basic flowchart of the intelligent process parameter optimization method for rubber mixing according to the present invention;
[0066] Figure 3 This is a detailed flowchart of an intelligent process parameter optimization method for rubber mixing according to the present invention. Detailed Implementation
[0067] To more clearly illustrate the embodiments of the present invention, specific implementation methods will be described below with reference to the accompanying drawings. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings and other implementation methods can be obtained based on these drawings without any creative effort.
[0068] like Figure 1 As shown, in the method of this invention, the process learning module cleans and processes the MES data, uses a clustering algorithm to generate process parameters for different periods and stores them in the AI intelligent control platform. At the same time, a deep reinforcement learning model is trained. During production, the intelligent mixing software first uses a recommendation algorithm to find the most suitable process parameters based on the production information, and then sends them to the mixing machine through the auxiliary machine PLC to obtain the mixing process data. Then, based on the mixing process data fed back by the auxiliary machine PLC, the already trained reinforcement learning model is used to further optimize the process. Finally, the AI process is sent to the mixing machine through the auxiliary machine PLC for execution.
[0069] like Figure 2 As shown, this invention provides a smart process parameter optimization method for rubber mixing, comprising the following steps:
[0070] S1 uses an intelligent refining AI management platform to obtain production data;
[0071] S2, extract training data from the production data, train the AI process learning model, and store it in the intelligent mixing AI control platform;
[0072] S3, the intelligent mixing AI control platform distributes the trained AI process learning model to the AI intelligent terminal;
[0073] S4, start the AI process calculation program and collect the data of the internal mixing process in real time. At the same time, input the collected data into the trained AI process learning model to optimize the process parameters and output the optimized internal mixing AI process.
[0074] S5, the auxiliary machine PLC terminal receives the internal mixing AI process and sends it to the internal mixer;
[0075] S6, the internal mixer performs the internal mixing AI process.
[0076] Detailed steps and procedures, such as Figure 2 As shown, the specific process is as follows:
[0077] S11, the data platform obtains production data through systems such as MES and WMS, including mixing process data, step sequence reports, quality inspection data, raw material data, feeding data, and weather information.
[0078] S21. Clean the production data, use the mean-shift algorithm to cluster the process parameters of different periods, and save all versions of process parameters in the intelligent mixing AI management and control platform according to the formula category.
[0079] S22, clean the production data, use the DQN algorithm for reinforcement learning, and save the AI process learning model obtained from the reinforcement learning based on the formula in the intelligent mixing AI control platform.
[0080] Specifically, step S21 includes the following steps:
[0081] S211, the collected production data is processed for outlier handling and feature extraction, and then processed into the required data format;
[0082] S212, for each formulation, apply the corresponding process parameters to the clustering process;
[0083] The clustering process is as follows:
[0084] The data points are initialized with the mean of each point, and the bandwidth parameter h is selected; for data point x, the corresponding Mean-Shift vector is represented as:
[0085]
[0086] Where N(x) is the set of data points within the bandwidth parameter h, i.e., the neighborhood of point x; x i This represents the i-th data point; parameter K represents the kernel function, specifically a Gaussian kernel function; the magnitude and direction of the Mean-Shift vector depend on the data distribution within the neighborhood.
[0087] For each data point x, continuously move towards higher density, i.e. execute: x←x+m(x), repeat several times until convergence to a local maximum density point; if the convergence distance between adjacent data points is less than a set threshold, then the corresponding data points are merged into a cluster; the final centroid and corresponding data points are the clustering result.
[0088] S213 stores the characteristics and process parameters of multiple classes of each formula in the intelligent mixing AI control platform; the clustered process parameters are used to intelligently recommend processes based on changes in production conditions.
[0089] Step S22 specifically includes the following steps:
[0090] S221 handles outliers and missing values in production data, specifically including missing value interpolation and imputation, data smoothing, and data standardization.
[0091] S222: Extract features from the data processed in step S221, and filter out effective feature data through statistical analysis and dimensionality reduction.
[0092] S223 divides the effective feature data into training, validation and test sets for subsequent model training and evaluation.
[0093] S224 uses the DQN algorithm for reinforcement learning, and the specific process is as follows:
[0094] Determine the state space of the internal mixing process, including process data, feed data, and mixing quality data;
[0095] Define the action space of the intensive mixing process, including rotation speed, pressure, time, temperature, and energy;
[0096] Design a reward function based on the quality requirements of intensive mixing, and design immediate rewards considering production efficiency and product quality;
[0097] Build a DQN network model, construct a simulation environment based on historical production data, use the DQN algorithm for reinforcement learning training, and gradually optimize the strategy of the DQN network model.
[0098] The trained DQN network model is stored in the intelligent AI management and control platform.
[0099] Establish a feedback mechanism to collect data on the performance of the DQN network model in actual production, evaluate the performance of the DQN network model, and retrain or fine-tune it regularly based on new production data.
[0100] S31. After training is completed, the trained process learning model (DQN network model) is sent to the corresponding AI smart terminal.
[0101] S41, during production, the AI process calculation program obtains the current production formula information and feeding information from the MES interface, obtains the corresponding raw material inspection data from the WMS system interface, obtains weather data from the intelligent mixing AI control platform, and uses the cosine similarity algorithm to calculate the AI process that best matches the current production environment.
[0102] S42, the AI computing program on the AI smart terminal writes the generated process parameters to the upper auxiliary machine PLC terminal and notifies the upper auxiliary machine PLC terminal that the process parameters have been written.
[0103] S43, after the auxiliary machine PLC terminal receives the new process parameters written by the AI process calculation program, it replaces the currently executed process parameters.
[0104] S44, the internal mixer executes the AI process to produce rubber compound. The AI process calculation program captures real-time process data through the auxiliary PLC terminal at a fixed frequency.
[0105] The AI process calculation program on the S45 AI smart terminal further optimizes the new process parameters based on real-time process data, generates the mixing AI process, and then re-issues it to the auxiliary machine PLC terminal through the AI calculation program.
[0106] Specifically, step S41 includes the following steps:
[0107] S411 obtains current production formula and feeding information from the data interface of the MES system, raw material inspection data and origin data from the data interface of the WMS system, and weather data from the intelligent mixing AI control platform.
[0108] S412, by linking formula information and feeding information with quality inspection data and raw material data, obtain the current formula material composition and material inspection data;
[0109] S413, by processing the data obtained in steps S411 and S412, the feature vector A = (a1, a2, ..., a...) of the current feeding information is obtained. n The data processing process includes data formatting, outlier handling, missing value imputation, feature extraction, numerical encoding of classification features, and normalization, which are commonly used in existing technologies.
[0110] The clustering results of the current production formula from the intelligent internal refining AI control platform are retrieved. For each cluster, the corresponding feature vector B = (b1, b2, ..., b...) is extracted. n ), calculate cosine similarity:
[0111]
[0112] The process with the highest cosine similarity is selected as the one that best matches the current production environment.
[0113] Step S42 includes the following steps:
[0114] S421, the AI smart terminal runs an AI computing program to intelligently generate process parameters based on current production needs, historical data, and raw material data;
[0115] S422, encode the generated process parameters in a format that the PLC can understand;
[0116] S423 transmits the encoded process parameters to the auxiliary PLC terminal via industrial Ethernet.
[0117] S424 After the transmission is completed, the AI intelligent terminal notifies the auxiliary PLC terminal that the new process parameters have been written by updating the status of the corresponding monitoring points. After the PLC detects the status update, it issues the process parameters for execution.
[0118] Preferably, step S45 includes the following steps:
[0119] S451, after the AI process calculation program obtains complete real-time process data, it performs analysis and processing.
[0120] And extract the characteristics of the process curve;
[0121] S452 calls the trained AI process learning model to further optimize the process parameters and generates an optimized mixing AI process, which is then re-sent to the auxiliary machine PLC terminal through the AI calculation program.
[0122] S5, the auxiliary machine PLC terminal receives the internal mixing AI process and sends it to the internal mixer.
[0123] S61, quality inspection of the produced rubber compound, and the inspection results are synchronized to the MES system;
[0124] S62, the intelligent mixing AI control platform collects rubber compound inspection data and process data obtained from the mixing AI process;
[0125] S63, add the newly generated data from step S62 to the existing production data, perform incremental learning, and repeat steps S1 to S5.
[0126] At this point, the intelligent process is complete.
[0127] This invention's system consists of an AI process learning model and an AI process calculation program, employing a combination of clustering algorithms, recommendation algorithms, and reinforcement learning for model training. Nearly 3 million MES production data points are synchronized through the AI intelligent mixing control platform. After data mining, the data is extracted, and then the mean-shift algorithm is used to cluster process parameters for different periods. Simultaneously, the DQN reinforcement learning algorithm is used to train an AI reinforcement learning model, which is automatically distributed to the corresponding AI intelligent terminals by the AI control platform. During initial operation, the AI process calculation program recommends a set of process parameters based on material input and weather information, which is then distributed to the mixing machine via the auxiliary machine PLC for execution. Simultaneously, real-time process data from the MES system and the auxiliary machine PLC is collected, processed, and input into the AI process learning model to achieve real-time optimization of the production process. The AI control platform extracts data from the rubber compound after quality inspection to evaluate the model's process control effectiveness. If the control effect does not meet expectations, newly generated data is used for incremental training on the original model, and then re-distributed to the corresponding AI intelligent terminals. After the system went online, the final Mooney pass rate increased from 91.75% to 98.55%, and the carbon black dispersion pass rate increased from 78.85% to 96.5%. The mixing time was reduced by 2.6 seconds, which improved the quality of the rubber compound while reducing energy consumption and increasing production efficiency.
[0128] This invention addresses the shortcomings of current rubber mixing processes through intelligentization, automation, and adaptability. It focuses on utilizing a Manufacturing Execution System (MES), a Warehouse Management System (WMS), and a PLC control system, combined with clustering, recommendation, and deep reinforcement learning algorithms, to automatically generate the optimal mixing process based on changes in production conditions. This process is then executed by the mixing machine via the auxiliary PLC, and the process can be optimized in real time during production.
[0129] The above description is merely a detailed explanation of preferred embodiments and principles of the present invention. For those skilled in the art, there may be changes in specific implementation methods based on the ideas provided by the present invention, and these changes should also be considered within the scope of protection of the present invention.
Claims
1. A method for optimizing intelligent process parameters for rubber mixing, characterized in that, Includes the following steps: S1 uses an intelligent refining AI management platform to obtain production data; S2, extract training data from the production data, train the AI process learning model, and store it in the intelligent mixing AI control platform; S3, the intelligent mixing AI control platform distributes the trained AI process learning model to the AI intelligent terminal; S4, start the AI process calculation program and collect the data of the internal mixing process in real time. At the same time, input the collected data into the trained AI process learning model to optimize the process parameters and output the optimized internal mixing AI process. S5, the auxiliary machine PLC terminal receives the internal mixing AI process and sends it to the internal mixer; S6, the internal mixer performs the internal mixing AI process; Step S2 includes the following steps: S21. Clean the production data, use the mean-shift algorithm to cluster the process parameters of different periods, and save all versions of process parameters in the intelligent mixing AI management and control platform according to the formula category. S22, clean the production data, use the DQN algorithm for reinforcement learning, and save the AI process learning model obtained from the reinforcement learning based on the formula in the intelligent mixing AI control platform.
2. The intelligent process parameter optimization method for rubber mixing according to claim 1, characterized in that, In step S1, the production data includes mixing process data, step sequence report, quality inspection data, raw material data, feeding data, and weather information.
3. The intelligent process parameter optimization method for rubber mixing according to claim 1, characterized in that, Step S21 includes the following steps: S211, the collected production data is processed for outlier handling and feature extraction, and then processed into the required data format; S212, for each formulation, apply the corresponding process parameters to the clustering process; The clustering process is as follows: Initialize the data points to the mean of each point, and select the bandwidth parameter. For data points The corresponding Mean-Shift vector Represented as: ； in, It is a bandwidth parameter The set of data points within, i.e., points The neighborhood; This represents the i-th data point; parameter K represents the kernel function, specifically a Gaussian kernel function; the magnitude and direction of the Mean-Shift vector depend on the data distribution within the neighborhood; For each data point It continuously moves towards higher density, i.e., it executes: Repeat this process several times until the data converges to a local maximum density point. If the convergence distance between adjacent data points is less than a set threshold, the corresponding data points are merged into a cluster. The final centroid and corresponding data points are the clustering results. S213 stores the characteristics and process parameters of multiple classes of each formula in the intelligent mixing AI control platform; the clustered process parameters are used to intelligently recommend processes based on changes in production conditions.
4. The intelligent process parameter optimization method for rubber mixing according to claim 1, characterized in that, Step S22 includes the following steps: S221 handles outliers and missing values in production data, specifically including missing value interpolation and imputation, data smoothing, and data standardization. S222: Extract features from the data processed in step S221, and filter out effective feature data through statistical analysis and dimensionality reduction. S223 divides the effective feature data into training, validation and test sets for subsequent model training and evaluation. S224 uses the DQN algorithm for reinforcement learning, and the specific process is as follows: Determine the state space of the internal mixing process, including process data, feed data, and mixing quality data; Define the action space of the intensive mixing process, including rotation speed, pressure, time, temperature, and energy; Design a reward function based on the quality requirements of intensive mixing, and design immediate rewards considering production efficiency and product quality; Build a DQN network model, construct a simulation environment based on historical production data, use the DQN algorithm for reinforcement learning training, and gradually optimize the strategy of the DQN network model. The trained DQN network model is stored in the intelligent AI management and control platform. Establish a feedback mechanism to collect data on the performance of the DQN network model in actual production, evaluate the performance of the DQN network model, and retrain or fine-tune it regularly based on new production data.
5. The intelligent process parameter optimization method for rubber mixing according to claim 1, characterized in that, Step S4 includes the following steps: S41, during production, the AI process calculation program obtains the current production formula information and feeding information from the MES interface, obtains the corresponding raw material inspection data from the WMS system interface, obtains weather data from the intelligent mixing AI control platform, and uses the cosine similarity algorithm to calculate the AI process that best matches the current production environment. S42, the AI computing program on the AI smart terminal writes the generated process parameters to the upper auxiliary machine PLC terminal and notifies the upper auxiliary machine PLC terminal that the process parameters have been written. S43, after the auxiliary machine PLC terminal receives the new process parameters written by the AI process calculation program, it replaces the currently executed process parameters. S44, the internal mixer executes the AI process to produce rubber compound. The AI process calculation program captures real-time process data through the auxiliary PLC terminal at a fixed frequency. The AI process calculation program on the S45 AI smart terminal further optimizes the new process parameters based on real-time process data, generates the mixing AI process, and then re-issues it to the auxiliary machine PLC terminal through the AI calculation program.
6. The intelligent process parameter optimization method for rubber mixing according to claim 5, characterized in that, Step S41 includes the following steps: S411 obtains current production formula and feeding information from the data interface of the MES system, raw material inspection data and origin data from the data interface of the WMS system, and weather data from the intelligent mixing AI control platform. S412, by linking formula information and feeding information with quality inspection data and raw material data, obtain the current formula material composition and material inspection data; S413, by processing the data obtained in steps S411 and S412, the feature vector of the current feeding information is obtained. The data processing steps include data formatting, outlier handling, missing value imputation, feature extraction, numerical encoding and normalization of categorical features. The clustering results of the current production formula are captured from the intelligent internal refining AI control platform. Each cluster is then iterated through to extract its corresponding feature vector. Calculate the cosine similarity: ； The process with the highest cosine similarity is selected as the one that best matches the current production environment.
7. The intelligent process parameter optimization method for rubber mixing according to claim 6, characterized in that, Step S42 includes the following steps: S421, the AI smart terminal runs an AI computing program to intelligently generate process parameters based on current production needs, historical data, and raw material data; S422, encode the generated process parameters in a format that the PLC can understand; S423 transmits the encoded process parameters to the auxiliary PLC terminal via industrial Ethernet. S424 After the transmission is completed, the AI intelligent terminal notifies the auxiliary PLC terminal that the new process parameters have been written by updating the status of the corresponding monitoring points. After the PLC detects the status update, it issues the process parameters for execution.
8. The intelligent process parameter optimization method for rubber mixing according to claim 5, characterized in that, Step S45 includes the following steps: S451, after the AI process calculation program obtains complete real-time process data, it performs analysis and processing, and extracts the process curve features; S452 calls the trained AI process learning model to further optimize the process parameters and generates an optimized mixing AI process, which is then re-sent to the auxiliary machine PLC terminal through the AI calculation program.
9. The intelligent process parameter optimization method for rubber mixing according to claim 1, characterized in that, Step S6 includes the following steps: S61, quality inspection of the produced rubber compound, and the inspection results are synchronized to the MES system; S62, the intelligent mixing AI control platform collects rubber compound inspection data and process data obtained from the mixing AI process; S63, add the newly generated data from step S62 to the existing production data, perform incremental learning, and repeat steps S1 to S5.