EPDM rubber sealing strip dual-head intelligent control parallel extrusion method

Abstract

The present application provides a method for intelligently controlling and parallel extrusion of dual-head EPDM rubber sealing strips, which relates to the field of rubber sealing technology, including: obtaining an EPDM rubber extrusion task; obtaining sealing strip production requirements, and making dual-head parallel extrusion decisions for the first head extrusion component and the second head extrusion component; activating an extrusion loss prediction and evaluation module; performing loss prediction and evaluation on the first parallel extrusion scheme; determining whether the first parallel extrusion loss coefficient is greater than or equal to a predetermined extrusion loss threshold; if greater than or equal to, optimizing and adjusting the first parallel extrusion scheme. The present application can solve the technical problem in the prior art that the mass production efficiency of EPDM rubber sealing strips is low due to the fact that the production process usually uses a single-head extrusion or multiple heads independently control extrusion. Through dual-head parallel extrusion, optimization is performed according to loss prediction, thereby improving the efficiency of EPDM rubber sealing strip production.

Description

Technical Field

[0001] The present application relates to the technical field of rubber sealing, and in particular to a method for parallel extrusion of EPDM rubber sealing strips with dual heads of intelligent control. Background Art

[0002] In the field of automotive parts manufacturing, EPDM rubber is widely used in the manufacture of various sealing strips, such as doors, windows, engine hoods and trunk sealing strips, due to its excellent weather resistance, heat resistance, ozone resistance and elasticity. It plays a role in waterproofing, dustproofing, sound insulation and shock absorption in the automotive sealing system, and has an important impact on the sealing performance and driving comfort of the vehicle. With the development of the automotive industry and the increase in the number of cars, the demand for sealing strips in doors, windows and other locations has increased significantly. The traditional single-head extrusion method is difficult to meet the mass production needs of the automotive industry in terms of production efficiency. In the process of trying to increase production, multi-head extrusion has gradually been applied to production, but multi-head extrusion mostly adopts independent control mode, which is difficult to coordinate in actual production. It is easy to cause inconsistent parameters between heads, uneven material flow, temperature control differences and other problems, resulting in inconsistent size and performance of sealing strips, which is difficult to meet the automotive industry's demand for high-quality parts. The single-head or multi-head independent control extrusion method is difficult to ensure the consistency of the size and performance of each batch of sealing strips, especially the sealing strips with complex cross-sections, which require higher precision control of the extrusion process.

[0003] In summary, the prior art has a technical problem in which the production efficiency of EPDM rubber sealing strips is low when facing mass production needs because the production process usually uses a single-head extrusion or multiple heads independently controlled extrusion. Summary of the invention

[0004] The purpose of this application is to provide a dual-head intelligent control and parallel extrusion method for EPDM rubber sealing strips, so as to solve the technical problem in the prior art that the production efficiency of EPDM rubber sealing strips is low when facing large-scale production needs because the production process usually uses a single-head extrusion or multiple heads independently controlled extrusion.

[0005] In view of the above problems, the present application provides a method for intelligently controlling and extruding a dual-head EPDM rubber sealing strip in parallel, wherein the method comprises: obtaining an EPDM rubber extrusion task of an EPDM dual-head extrusion device, wherein the EPDM rubber extrusion task comprises an EPDM rubber mixture corresponding to the EPDM rubber sealing strip to be produced, and the EPDM dual-head extrusion device comprises a first head extrusion assembly and a second head extrusion assembly; obtaining the sealing strip production demand corresponding to the EPDM rubber sealing strip to be produced, and performing a dual-head parallel extrusion decision on the first head extrusion assembly and the second head extrusion assembly in combination with the EPDM rubber mixture to obtain a first parallel extrusion scheme; activating an extrusion loss prediction and evaluation module, wherein the extrusion loss prediction and evaluation module comprises a parallel An extrusion simulation unit, an extrusion loss prediction unit and a loss evaluation integrated unit; based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integrated unit, a loss prediction evaluation is performed on the first parallel extrusion scheme to obtain a first parallel extrusion loss coefficient; it is determined whether the first parallel extrusion loss coefficient is greater than or equal to a predetermined extrusion loss threshold; if the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integrated unit, the first parallel extrusion scheme is optimized and adjusted according to the predetermined extrusion loss threshold to generate a parallel extrusion optimization strategy; based on the parallel extrusion optimization strategy, the EPDM rubber mixture is subjected to dual-head parallel extrusion according to the first head extrusion assembly and the second head extrusion assembly.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] By obtaining the EPDM rubber extrusion task of the EPDM double-head extruder, wherein the EPDM rubber extrusion task includes the EPDM rubber mixture corresponding to the EPDM rubber sealing strip to be produced, and the EPDM double-head extruder includes a first head extrusion component and a second head extrusion component; obtaining the sealing strip production demand corresponding to the EPDM rubber sealing strip to be produced, combining the EPDM rubber mixture, making a double-head parallel extrusion decision for the first head extrusion component and the second head extrusion component, and obtaining a first parallel extrusion plan; activating the extrusion loss prediction and evaluation module, wherein the extrusion loss prediction and evaluation module includes a parallel extrusion simulation unit, an extrusion loss prediction unit and a loss evaluation integration unit; based on the parallel extrusion The simulation unit, the extrusion loss prediction unit and the loss evaluation integrated unit perform loss prediction and evaluation on the first parallel extrusion scheme to obtain the first parallel extrusion loss coefficient; determine whether the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold; if the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integrated unit, the first parallel extrusion scheme is optimized and adjusted according to the predetermined extrusion loss threshold to generate a parallel extrusion optimization strategy; based on the parallel extrusion optimization strategy, the EPDM rubber mixture is subjected to dual-head parallel extrusion according to the first head extrusion component and the second head extrusion component. That is to say, by obtaining the EPDM rubber extrusion task, according to the production demand and the characteristics of the EPDM rubber mixture, the working scheme of the first head and the second head is made parallel extrusion decision, by simulating the parallel extrusion process, the possible loss is predicted and evaluated, the first parallel extrusion loss coefficient is obtained, and it is determined whether it is greater than or equal to the predetermined loss threshold. In the case where the loss coefficient exceeds the standard, the optimization adjustment is started, the parallel extrusion scheme is adjusted, and the dual-head extrusion system is regulated, which significantly improves the production efficiency of the EPDM rubber sealing strip during large-scale production.

[0008] 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

[0009] 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.

[0010] Figure 1 This is a schematic diagram of the process of the dual-head intelligent control and parallel extrusion method of EPDM rubber sealing strips in this application;

[0011] Figure 2 This is a schematic flow chart of obtaining the first parallel extrusion loss coefficient in the dual-head intelligent control parallel extrusion method for EPDM rubber sealing strips in this application. DETAILED DESCRIPTION

[0012] This application solves the technical problem in the prior art that the production efficiency of EPDM rubber sealing strips is low when facing mass production needs, by providing a method for intelligently controlling and parallel extrusion of dual heads of EPDM rubber sealing strips, because the production process usually uses single-head extrusion or multiple heads independently control extrusion. By obtaining the EPDM rubber extrusion task, according to the production needs and the characteristics of the EPDM rubber mixture, a parallel extrusion decision is made for the working schemes of the first head and the second head. By simulating the parallel extrusion process, the possible losses are predicted and evaluated, and the first parallel extrusion loss coefficient is obtained. It is judged whether it is greater than or equal to the predetermined loss threshold. When the loss coefficient exceeds the standard, the optimization adjustment is started, the parallel extrusion scheme is adjusted, and the dual-head extrusion system is regulated, which significantly improves the production efficiency of EPDM rubber sealing strips during large-scale production.

[0013] 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.

[0014] For examples, please see the attached Figure 1 The present application provides a method for intelligently controlling and extruding a double-head EPDM rubber sealing strip in parallel, wherein the method for intelligently controlling and extruding a double-head EPDM rubber sealing strip in parallel specifically comprises the following steps:

[0015] Step 1: Obtain an EPDM rubber extrusion task of an EPDM double-head extruder, wherein the EPDM rubber extrusion task includes an EPDM rubber mixture corresponding to the EPDM rubber sealing strip to be produced, and the EPDM double-head extruder includes a first head extrusion assembly and a second head extrusion assembly.

[0016] Specifically, the EPDM double-head extrusion device is a specially designed EPDM rubber extrusion equipment with two independent head assemblies, namely the first head extrusion assembly and the second head extrusion assembly. The head is a key component for forming the rubber shape during the extrusion process, and the double-head design allows the two heads to work at the same time to improve production efficiency. The first head extrusion assembly and the second head extrusion assembly include two extruders and their respective heads for extruding rubber mixtures.

[0017] The EPDM rubber extrusion task is obtained from the production center, including the formula of rubber materials, the required sealing strip specifications, production quantity, etc., and the equipment is required to extrude EPDM rubber according to the specified parameters. The production center determines the specifications, quantity and delivery date of the EPDM rubber sealing strips to be produced according to the production plan, order requirements or inventory situation, and generates a specific EPDM rubber extrusion task, including the specifications of the EPDM rubber sealing strips to be produced and the corresponding rubber mixture formula. EPDM rubber mixture refers to the raw materials used to make EPDM rubber sealing strips, usually composed of ethylene, propylene and other additives. By using the EPDM double-head extrusion device, using the first head extrusion assembly and the second head extrusion assembly, compared with the single-head production line that can only produce cross-section products at a time, with low output and high energy consumption, the double-head assembly achieves the output of two lines by adding two extruders and one head, which has the advantages of small footprint, large output and low energy consumption, doubles the output, and can produce products of different cross sections each time, and reduces the comprehensive energy consumption by 30%.

[0018] Step 2: Obtain the sealing strip production demand corresponding to the EPDM rubber sealing strip to be produced, combine the EPDM rubber mixture, make a dual-head parallel extrusion decision for the first head extrusion assembly and the second head extrusion assembly, and obtain a first parallel extrusion plan.

[0019] Specifically, the sealing strip production requirements corresponding to the current EPDM rubber sealing strip to be produced are obtained from the EPDM rubber extrusion task, that is, the various requirements and parameters that need to be achieved during the production process, such as size, hardness, elasticity, surface finish, temperature resistance, etc. Production requirements are usually determined by customer orders or design specifications and are used to guide various decisions in the production process. For example, the sealing strip produced may require high weather resistance and be suitable for sealing around car doors, so the production requirements may include specific hardness, temperature resistance and UV resistance. Collect the basic parameters of EPDM rubber mixture, such as formula, viscosity, fluidity, hardness, etc. Different rubber mixtures have different processing characteristics. EPDM rubber mixture refers to a composite material formed by mixing EPDM base rubber with other additives (such as vulcanizers, plasticizers, fillers, antioxidants, etc.) in a certain proportion. It has different physical and chemical properties and is used to produce different types of sealing strips.

[0020] Parallel extrusion decision-making is performed on the first die extrusion assembly and the second die extrusion assembly, that is, the tasks of the first die and the second die are intelligently allocated and adjusted according to the input production requirements and rubber mixture information. The production requirements of the sealing strip are analyzed to determine the main specifications and characteristics of the sealing strip. According to the information of the rubber mixture, the influence of the physical properties of rubber (such as viscosity, fluidity, etc.) on the extrusion process is taken into account. For high-viscosity rubber mixtures, higher extruder temperatures and greater pressures may be required, while for low-viscosity mixtures, lower temperatures and pressures may be required. Based on the production requirements and rubber mixture information, they are input into the trained dual-die parallel extrusion decision-making module to generate the first parallel extrusion plan to determine how to allocate work between the dual heads. The first parallel extrusion plan includes the operating settings of each die, such as temperature, speed, pressure, etc., to ensure that the production requirements of the sealing strip can be met. By combining the production requirements and rubber mixture information of the EPDM rubber sealing strip to be produced, intelligent dual-die parallel extrusion decisions are made to generate the best production plan, which not only improves production efficiency, but also optimizes resource utilization and product quality, and helps to achieve an efficient automated production process.

[0021] Step three: activating the extrusion loss prediction and evaluation module, wherein the extrusion loss prediction and evaluation module includes a parallel extrusion simulation unit, an extrusion loss prediction unit and a loss evaluation integration unit.

[0022] Specifically, during the production process, dual-head parallel extrusion will face different loss problems. In order to avoid these losses, the extrusion loss prediction and evaluation module is first activated to comprehensively evaluate the entire production process. The extrusion loss prediction and evaluation module is used to predict and evaluate the losses that may occur during the dual-head parallel extrusion process, and provide corresponding optimization suggestions, aiming to optimize the extrusion process and reduce these losses through simulation and prediction. Losses include loss of production efficiency, waste of raw materials, and the production of defective products. The parallel extrusion simulation unit is a simulation tool used to simulate the operation of the dual-head parallel extrusion process and predict the production effect under different operating conditions. Usually based on mathematical models or computer simulation technology, such as computational fluid dynamics (CFD) software, finite element analysis (FEA) software, etc., the interactive effects of machines, materials and production environments are simulated to help evaluate potential losses in the extrusion process.

[0023] The extrusion loss prediction unit uses data analysis tools or machine learning models (such as regression analysis, decision trees or neural networks) to make specific predictions on losses based on the data obtained from the parallel extrusion simulation unit. It predicts possible losses by analyzing various parameters in the production process (such as temperature, pressure, speed, etc.), such as excessive energy consumption, equipment failure, and waste of raw materials. The loss evaluation integration unit is responsible for comprehensively evaluating the loss data obtained from the extrusion loss prediction unit, conducting an overall analysis, and providing quantitative evaluation results of the losses. It may also cooperate with optimization algorithms (such as genetic algorithms, particle swarm optimization algorithms, etc.) to make adjustments based on the results of loss prediction to achieve more efficient production. By predicting and evaluating losses in the production process in advance, production parameters can be adjusted in a timely manner to reduce resource waste and the generation of defective products.

[0024] Step 4: Based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, a loss prediction evaluation is performed on the first parallel extrusion scheme to obtain a first parallel extrusion loss coefficient.

[0025] Specifically, a dual-head extrusion model is constructed based on the EPDM dual-head extrusion device, and it is combined with the parallel extrusion simulation unit. The simulation data and the first parallel extrusion scheme are used to simulate the extrusion of the EPDM rubber mixture. The dual-head extrusion model is a simulation model of the EPDM dual-head extrusion device, which mainly simulates the mechanical structure and operation behavior of the device. The dual-head extrusion model reproduces the real extrusion process through simulation according to the actual device structure and process parameters, ensuring that the simulation data is as close to the actual production situation as possible. The first head and the second head will affect each other. The dual-head model can reflect the behavioral characteristics of the two when working synchronously, including possible blockages or quality fluctuations. The extrusion parameters and behavior data obtained through modeling provide reliable data support for the simulation process and accurately analyze different extrusion schemes. In general, the main function of the dual-head extrusion model is to accurately simulate the working mechanism of the extrusion equipment itself, provide basic equipment and parameter models for simulation, and ensure the authenticity and reliability of the simulation results.

[0026] The parallel extrusion simulation unit is a simulation device used to analyze and optimize the dual-head extrusion model. It is mainly responsible for simulating the effects of multiple extrusion schemes when working in parallel. By inputting different extrusion schemes into the parallel extrusion simulation unit, the feasibility and effect of each scheme in the dual-head mode are tested and analyzed. Tests are conducted on potential problems such as quality loss, resource loss, and blockage during the simulation process to identify possible failures in the production process, thereby providing early warnings. According to the simulation results, the loss coefficients of different schemes are output, and the optimal extrusion scheme is selected so that actual production can run with minimal loss and maximum efficiency. In general, the parallel extrusion simulation unit is based on the dual-head extrusion model and simulates through a variety of parameter combination schemes to evaluate the production effects under different production conditions, especially the identification and prediction of loss factors, thereby providing a basis for the optimization plan.

[0027] The first parallel extrusion scheme is used to simulate the extrusion process of EPDM rubber mixture through a dual-head extrusion model and a parallel extrusion simulation unit to obtain the first parallel extrusion simulation data. The first parallel extrusion simulation data is input into the extrusion loss prediction unit, which includes multiple sub-models, such as a parallel extrusion quality loss prediction model, a parallel extrusion blockage loss prediction model, and a parallel extrusion resource loss prediction model. Based on historical data and real-time monitoring data, statistical analysis and machine learning algorithms are used to predict potential losses. Each model outputs a prediction coefficient, which indicates the prediction degree of the corresponding type of loss. These three prediction coefficients together constitute the first extrusion loss prediction result. The first extrusion loss prediction result is input into the loss evaluation integration unit, and different loss types are weighted and evaluated according to the set weights (such as extrusion quality loss weight, extrusion blockage loss weight, and extrusion resource loss weight) to generate a comprehensive loss coefficient, namely the first parallel extrusion loss coefficient, which integrates all the loss types considered and provides a quantitative indicator of the total loss that may be caused by the first parallel extrusion scheme. By using the parallel extrusion simulation unit, the extrusion loss prediction unit, and the loss evaluation integration unit, the potential risks and losses of the first parallel extrusion scheme are comprehensively evaluated, so that measures can be taken to prevent and reduce losses and improve production efficiency and product quality.

[0028] Step 5: Determine whether the first parallel extrusion loss coefficient is greater than or equal to a predetermined extrusion loss threshold.

[0029] Specifically, the first parallel extrusion loss coefficient is calculated by weighting various loss coefficients (quality loss coefficient, blockage loss coefficient, resource loss coefficient) output by the loss prediction model through simulation data and prediction models, reflecting the overall loss caused by different types of losses (quality loss, blockage loss and resource loss) in the production process. The first parallel extrusion loss coefficient measures the comprehensive loss degree in the production process. The higher the coefficient, the greater the loss. The predetermined extrusion loss threshold is a pre-set target value, which is usually set according to industry standards, historical data or production requirements, reflecting the maximum acceptable loss range in the production process. If the loss coefficient exceeds this threshold, it means that the production efficiency is low, the waste of resources is serious, or the product quality does not meet expectations, and adjustments are needed.

[0030] Compare the calculated first parallel extrusion loss coefficient with the predetermined extrusion loss threshold. If the loss coefficient is greater than or equal to the threshold, it means that a more serious loss has occurred in the production process, which may lead to resource waste, quality problems or low production efficiency, so optimization measures need to be taken. If the loss coefficient is less than the threshold, it means that the loss in the production process is within an acceptable range, and the current production process can be maintained without immediate adjustment. By judging the relationship between the loss coefficient and the predetermined threshold, potential problems in the production process, such as resource waste, equipment blockage, product quality fluctuations, etc., can be discovered in a timely manner, reducing losses, improving resource utilization, and improving production efficiency.

[0031] Step six: If the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, the first parallel extrusion scheme is optimized and adjusted according to the predetermined extrusion loss threshold to generate a parallel extrusion optimization strategy.

[0032] Specifically, if the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, it indicates that a relatively serious loss has occurred in the production process, which may lead to resource waste, quality problems or low production efficiency, and therefore optimization measures need to be taken. By collecting the control parameters of the EPDM twin-head extruder (for example, temperature, pressure, material flow rate, etc.), an extrusion control constraint domain is established, that is, the parameter space in which extrusion can be performed within the operating range of the equipment. The extrusion control constraint domain ensures that the extrusion process will not exceed the performance or safety limits of the equipment.

[0033] Optimal adjustment refers to optimizing the first parallel extrusion scheme according to a predetermined extrusion loss threshold to reduce the loss coefficient to less than the predetermined threshold, including adjusting extrusion parameters such as speed, temperature, pressure, etc., or changing the material formula to reduce quality loss, blockage loss and resource loss. According to the production requirements of the sealing strip, the parameters in the first parallel extrusion scheme are changed or randomly adjusted within the extrusion control constraint domain to explore more parallel extrusion schemes, and these parallel extrusion schemes are integrated together to form a parallel extrusion scheme optimization space, which includes all possible optimization schemes, that is, the potential scheme space that can be selected during the optimization process.

[0034] Randomly select another extrusion scheme in the parallel extrusion scheme optimization space, and perform loss prediction evaluation on it through the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit to obtain the corresponding second parallel extrusion loss coefficient, and compare it with the predetermined extrusion loss threshold. If the second parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold, the scheme is considered feasible and added to the parallel extrusion optimization strategy. On the contrary, if the loss coefficient of the second scheme is greater than or equal to the set threshold, the scheme will be eliminated. When the second parallel extrusion scheme is eliminated, continue to randomly extract a new third parallel extrusion scheme from the optimization space for the same analysis operation. Continuously select parallel extrusion schemes in the parallel extrusion scheme optimization space, and perform further optimization analysis until a scheme that meets the requirements is found. In the optimization process, ensure that each extrusion scheme optimizes the production parameters without exceeding the loss threshold, and finally ensure that the produced EPDM rubber sealing strips are consistent and high quality. Through optimization adjustment, find an extrusion scheme with lower risk and more in line with production needs, and construct the optimal parallel extrusion optimization strategy, which helps to improve the adaptability and flexibility of the production process, optimize production parameters, improve production efficiency and product quality, and reduce risks and losses.

[0035] Step seven: Based on the parallel extrusion optimization strategy, the EPDM rubber mixture is subjected to dual-head parallel extrusion according to the first head extrusion assembly and the second head extrusion assembly.

[0036] Specifically, the parallel extrusion optimization strategy refers to the best parallel extrusion scheme set finally selected through the optimization and evaluation process, which includes a variety of parallel extrusion schemes that have been screened and meet the loss threshold, representing the optimal extrusion path obtained through continuous optimization under certain control constraints. After obtaining the parallel extrusion optimization strategy, the working state (such as temperature, pressure, speed, etc.) of the first and second heads are adjusted according to the best scheme, so that the two heads work in parallel to minimize losses and improve production efficiency. For example, suppose that in the optimization strategy, the first head extrusion assembly is set to a higher speed to improve production efficiency, while the second head is adjusted to a lower temperature to ensure the quality of the rubber mixture. Through this configuration of dual-head parallel extrusion, the production volume can be increased without affecting the quality of the final product. The EPDM rubber mixture is fed into the dual-head extrusion device. Through the optimized parallel extrusion scheme, the first and second head extrusion assemblies work simultaneously to process different parts of the rubber mixture respectively. Finally, the rubber strips produced by the two heads are merged into the final EPDM rubber sealing strip. Through dual-head parallel extrusion, more rubber mixtures can be processed at the same time, the production speed can be increased, and the needs of mass production can be met. By optimizing strategies, we can reduce losses in the production process (such as quality loss, blockage loss, resource waste, etc.), thereby improving the overall efficiency and economy of the production process.

[0037] Furthermore, step one of this application includes:

[0038] The first die extrusion assembly includes a first extruder, a second extruder and a first die; the second die extrusion assembly includes a third extruder, a fourth extruder and a second die, wherein the first die extrusion assembly and the second die extrusion assembly share a vulcanization box.

[0039] Specifically, the first head extrusion assembly and the second head extrusion assembly are composed of multiple components and are responsible for the extrusion molding of the rubber mixture. The first head extrusion assembly includes a first extruder, a second extruder and a first head, and the second head extrusion assembly includes a third extruder, a fourth extruder and a second head. The extruder is used to plasticize and heat the EPDM rubber mixture, converting it into a flow state for easy extrusion molding; the head is the front end of the extrusion device, which directly contacts the rubber mixture and extrude it into a specific shape. The vulcanization box refers to a further treatment after rubber molding, which allows the rubber to complete the cross-linking reaction (vulcanization process) at high temperature to improve its mechanical properties, elasticity and durability. It is usually a closed heating system used to stabilize the molded rubber product through heat treatment.

[0040] After the two die extrusion assemblies complete extrusion, the sealing strips are processed in parallel through the same vulcanization box. The vulcanization box provides consistent heating conditions so that all molded sealing strips can complete the vulcanization process in the same environment. In the vulcanization box, rubber completes the cross-linking reaction through high temperature and a certain period of time, which is an important step for rubber products to harden, increase elasticity and durability. The vulcanized rubber sealing strip has the required physical properties, such as anti-aging, ozone resistance, high temperature resistance, etc., to ensure that it can work stably for a long time in the automotive sealing system. By running two production lines at the same time, the two die extrusion assemblies work in parallel, increasing production capacity. The design of the dual-die configuration can achieve the output of two lines, with the advantages of less space, large output and low energy consumption, doubling the output, and can produce products with different sections each time, reducing comprehensive energy consumption by 30%.

[0041] Further, step 2 of this application includes:

[0042] The basic parameters of the EPDM rubber mixture are collected to obtain rubber mixture information; dual-head parallel extrusion decision learning is performed according to the first head extrusion assembly and the second head extrusion assembly, and a dual-head parallel extrusion decision module is built; the sealing strip production demand and the rubber mixture information are input into the dual-head parallel extrusion decision module to obtain the first parallel extrusion plan.

[0043] Specifically, the basic parameters of EPDM rubber mixtures, such as viscosity, density, fluidity, etc., are collected and analyzed, which directly affect the performance of the rubber mixture during the extrusion process, including heating, plasticization, fluidity and other characteristics, which can be obtained through experimental equipment (such as viscometers, rheometers, temperature sensors, etc.). Dual-head parallel extrusion decision learning is performed based on the first head extrusion component and the second head extrusion component, that is, in the production process, according to different production requirements and the characteristics of the rubber mixture, the work tasks and parameter settings of the two extruders are reasonably arranged. Through parallel extrusion decisions, multiple production tasks can be processed simultaneously within a production cycle to maximize production efficiency. First, it is necessary to collect and analyze decision data in historical production, including different production requirements, rubber mixture information and corresponding parallel extrusion plans. By learning these data, the best production plan under different circumstances can be automatically identified.

[0044] The production demand and rubber mixture information are used as input data, and the corresponding parallel extrusion scheme is used as output data. A prediction model is built using machine learning algorithms (such as deep neural networks, decision trees, etc.). According to the input production demand and rubber mixture information, a parallel extrusion scheme is output, including the temperature, pressure, speed and other control parameters of the die. Through supervised learning, the model is trained using labeled historical data. During the training process, according to the actual needs of each production task, it is learned how to most effectively allocate the work of the two die heads. Methods such as cross-validation are used to avoid overfitting and optimize model parameters to ensure the accuracy of decision-making. The trained decision module can automatically generate the optimal dual-head parallel extrusion scheme based on the new production demand and mixture information, ensuring the smooth progress of the production process and avoiding waste of resources.

[0045] The collected sealing strip production requirements (such as the specifications, quantity, delivery time, etc. of the sealing strip) and rubber mixture information (such as composition, hardness, fluidity, etc.) are input into the dual-head parallel extrusion decision module to automatically generate a parallel extrusion plan for the first head extrusion component and the second head extrusion component, and decide how to allocate production tasks between the two heads, including the load of each head, working parameters (such as temperature, pressure, speed, etc.) and other adjustment parameters in the extrusion process, in order to optimize the production process and improve efficiency and quality. By optimizing the task allocation of the dual-head extrusion device based on data analysis and decision learning, manual intervention and experience dependence are reduced, and the automation and efficiency of the production process are improved.

[0046] Furthermore, the present application also includes the following steps:

[0047] According to the first head extrusion component and the second head extrusion component, a dual-head parallel extrusion decision record is retrieved to obtain a sealing strip production demand sample set, a rubber mixture information sample set and a parallel extrusion scheme sample set; with the sealing strip production demand sample set and the rubber mixture information sample set as input data and the parallel extrusion scheme sample set as output data, a deep feedforward neural network is supervised and trained, and when the number of training times meets the training number constraint, an extrusion decision loss coefficient is obtained; it is determined whether the extrusion decision loss coefficient is less than an extrusion decision loss threshold; if the extrusion decision loss coefficient is less than the extrusion decision loss threshold, the dual-head parallel extrusion decision module is generated.

[0048] Specifically, the parallel extrusion decision records related to the first head extrusion assembly and the second head extrusion assembly are retrieved from the historical production database, including extrusion parameters, material properties, extrusion schemes, etc. under different production requirements. The historical production database is a database that centrally stores and manages historical production data related to the dual-head parallel extrusion process. It usually contains all key data related to dual-head extrusion in past production activities, such as extrusion parameters, material properties, production requirements, extrusion schemes, production results, etc. The sealing strip production requirement sample set contains detailed production requirements for various sealing strips produced in the past, such as the size, hardness, material, quantity, etc. of the sealing strips. The rubber mixture information sample set contains parameter information of various mixtures used to produce EPDM rubber sealing strips, such as viscosity, density, fluidity, temperature, etc. The parallel extrusion scheme sample set records the specific parallel extrusion schemes used under different production requirements and rubber mixture characteristics in the historical production process.

[0049] The sample set of sealing strip production requirements and the sample set of rubber mixture information are used as input data, which contain detailed information on the specific requirements and mixtures used in historical production tasks. The sample set of parallel extrusion solutions is used as output data, which records the extrusion solutions actually taken under these input conditions, including the operating parameters of each head extruder (such as temperature, pressure, speed, material distribution, etc.). The deep feedforward neural network will learn how to generate the best extrusion solution based on production requirements and rubber mixture information. The deep feedforward neural network is a common neural network structure that includes multiple hidden layers, each with a certain number of neurons. This network is able to learn the complex relationship between input and output. The specific training process includes: the input data is passed to the hidden layer through the input layer, and then the result of the output layer is calculated. According to the gap between the predicted result and the actual label (i.e., the sample set of parallel extrusion solutions), the loss is calculated through the mean square error (MSE) or cross entropy loss function. Through the back-propagation algorithm, the loss value is propagated back to each layer in the network, and the weights and bias values ​​in the network are updated. Each training process will adjust the parameters of the network according to the difference between the known actual output (parallel extrusion solution) and the predicted output, so that the predicted result gradually approaches the actual value. During the training process, a training number or error threshold is usually set to control the number of training iterations. When the training reaches the preset number of times, the network stops training and outputs the final decision model.

[0050] After the training is completed, the extrusion decision loss coefficient is obtained, which indicates the gap between the predicted extrusion scheme and the actual extrusion scheme. The smaller the loss coefficient, the smaller the difference between the model's prediction and the actual production scheme, and the better the performance of the model. The extrusion decision loss threshold is a preset standard value used to determine whether the extrusion decision loss coefficient is within an acceptable range. If the loss coefficient is lower than the extrusion decision loss threshold, it means that the extrusion decision is accurate enough and the next step can be performed. If the loss coefficient is high, the decision module needs to be further optimized until it is lower than the extrusion decision loss threshold. If the extrusion decision loss coefficient is less than the set extrusion decision loss threshold, it is considered that the model's decision is accurate enough to be put into actual production. The final dual-head parallel extrusion decision module is output for real-time production decision-making, guiding how to reasonably configure production tasks, optimize the production process, and ensure that the production of sealing strips meets demand. Through deep learning and supervised training, accurate production decision rules are learned, which greatly improves the decision accuracy in the extrusion process. The generated decision module can quickly provide optimization solutions in real-time production, avoiding production errors caused by human intervention and lack of experience, thereby improving production efficiency.

[0051] Further, as attached Figure 2 As shown, step 4 of this application includes:

[0052] Modeling is performed based on the EPDM twin-head extrusion device to construct a twin-head extrusion model; based on the twin-head extrusion model and the parallel extrusion simulation unit, the EPDM rubber mixture is simulated for extrusion according to the first parallel extrusion scheme to obtain first parallel extrusion simulation data; the first parallel extrusion simulation data is input into the extrusion loss prediction unit to obtain a first extrusion loss prediction result; the first extrusion loss prediction result is input into the loss evaluation integration unit to generate the first parallel extrusion loss coefficient, wherein the loss evaluation integration unit includes an extrusion quality loss weight, an extrusion blockage loss weight and an extrusion resource loss weight.

[0053] Specifically, a model is established based on the EPDM twin-head extruder device, and the production process is predicted and optimized by simulating various physical phenomena (such as fluid flow, heat transfer, pressure changes, etc.) during the twin-head extrusion process. The purpose of establishing a twin-head extrusion model is to accurately predict the performance under different production conditions and analyze the operation of the equipment under different operating parameters (such as temperature, pressure, speed, etc.), so as to provide optimization suggestions for the production process. Before modeling, a large amount of data is collected, including the performance parameters of the extruder, the characteristics of EPDM rubber, the geometry of the extruder head, extrusion pressure, temperature, speed, equipment configuration, etc. According to the characteristics of the extrusion process and the collected data, a suitable mathematical model is selected, including flow models (Bernoulli equations and Navier-Stokes equations), heat conduction models, shear stress models (analyzing the rheological properties of rubber under high shear environments), etc.

[0054] Combine the constructed dual-head extrusion model with the parallel extrusion simulation unit to simulate the production process. Input the operating parameters in the first parallel extrusion scheme into the simulation system, including the temperature, pressure, speed, and characteristics of the mixture of the die. This process is performed on a computer without actually starting the extrusion device. The simulation unit simulates the flow, heating, pressure and other changes of EPDM rubber in the dual-head extrusion device based on the input parameters. After the simulation run is completed, the first parallel extrusion simulation data will be generated, reflecting the performance of the extrusion process under specific operating parameters, usually including temperature distribution, pressure distribution, flow rate and other data.

[0055] The extrusion loss prediction unit includes a parallel extrusion quality loss prediction model, a parallel extrusion blockage loss prediction model and a parallel extrusion resource loss prediction model, which are respectively used to predict losses caused by quality problems (improper process parameters), losses caused by blockage or equipment failure, and losses caused by resource waste (such as energy, raw materials, etc.). The first parallel extrusion simulation data is input into the parallel extrusion quality loss prediction model, the parallel extrusion blockage loss prediction model and the parallel extrusion resource loss prediction model to obtain the corresponding loss prediction coefficients, including the first parallel extrusion quality loss prediction coefficient, the first parallel extrusion blockage loss prediction coefficient and the first parallel extrusion resource loss prediction coefficient, which are the first extrusion loss prediction results.

[0056] Different weights are assigned to each loss coefficient according to the importance of different loss types or their impact on the total cost, and the sum of the weights assigned to these three loss coefficients is 1. The first parallel extrusion quality loss prediction coefficient, the first parallel extrusion blockage loss prediction coefficient, and the first parallel extrusion resource loss prediction coefficient of the first extrusion loss prediction result are input into the loss evaluation integration unit for weighted summation to obtain the first parallel extrusion loss coefficient. It reflects the overall degree of loss caused by quality loss, blockage loss, and resource loss under specific production conditions. The larger the loss coefficient, the greater the loss that may occur in the production process, and measures need to be taken to optimize it.

[0057] The loss evaluation integrated unit is used to integrate the prediction results of different types of losses, assign different weights according to the relative importance of each loss, and finally generate a comprehensive loss coefficient. The loss evaluation integrated unit includes extrusion quality loss weight (measures the importance of quality loss in the overall loss), extrusion blockage loss weight (measures the importance of blockage loss in the overall loss) and extrusion resource loss weight (measures the importance of resource waste in the overall loss). According to the three weights, various types of loss prediction coefficients are weighted to obtain the total loss coefficient, that is, the first parallel extrusion loss coefficient. By inputting the extrusion simulation data into the loss prediction unit, different types of losses (quality loss, blockage loss, resource loss) are predicted respectively, and through weighted calculation, a comprehensive parallel extrusion loss coefficient is obtained, which is used to optimize the production process, reduce losses, and improve production efficiency and product quality.

[0058] Furthermore, the present application also includes the following steps:

[0059] The extrusion loss prediction unit includes a parallel extrusion quality loss prediction model, a parallel extrusion congestion loss prediction model and a parallel extrusion resource loss prediction model; the first parallel extrusion simulation data is input into the parallel extrusion quality loss prediction model to obtain a first parallel extrusion quality loss prediction coefficient; the first parallel extrusion simulation data is input into the parallel extrusion congestion loss prediction model to obtain a first parallel extrusion congestion loss prediction coefficient; the first parallel extrusion simulation data is input into the parallel extrusion resource loss prediction model to obtain a first parallel extrusion resource loss prediction coefficient; the first parallel extrusion quality loss prediction coefficient, the first parallel extrusion congestion loss prediction coefficient and the first parallel extrusion resource loss prediction coefficient are output as the first extrusion loss prediction result.

[0060] Specifically, the extrusion loss prediction unit includes a parallel extrusion quality loss prediction model, a parallel extrusion blockage loss prediction model, and a parallel extrusion resource loss prediction model. The parallel extrusion quality loss prediction model is used to predict the losses caused by quality problems in the parallel extrusion process, including unqualified products, insufficient product hardness, appearance defects, etc., which are usually closely related to factors such as temperature, pressure, and fluidity of the mixture. It can be constructed by regression analysis model, support vector machine (SVM) or neural network. The parallel extrusion blockage loss prediction model is used to predict the losses caused by blockage or equipment failure in the parallel extrusion process. Blockage usually occurs in the extruder or die part. When the fluidity of the mixture is poor or the extruder load is too large, it will cause equipment blockage, which will affect production efficiency and quality. Blockage loss is usually nonlinear, so it may be predicted based on decision trees, logistic regression or other machine learning methods. The parallel extrusion resource loss prediction model is used to predict the losses caused by resource waste (such as energy, raw materials, etc.) in the parallel extrusion process. It can be constructed by energy efficiency evaluation model, life cycle analysis (LCA) model, etc. For example, production stagnation caused by excessive energy consumption, raw material waste or mechanical failure will increase production resource losses.

[0061] First, collect the process parameters (such as temperature, pressure, speed, etc.) in the extrusion process and the product quality problems (such as the hardness of the sealing strip, poor appearance, etc.) in the production process, and perform data preprocessing on these historical production data, including data cleaning and data standardization. Quality loss mainly includes product quality problems caused by too high or too low temperature, uneven mixture, insufficient cooling, etc. Through regression analysis, find out the key factors affecting product quality (such as temperature, flow rate, pressure, etc.), and establish a parallel extrusion quality loss prediction model. Blockage loss is usually caused by factors such as poor material flow or too fast flow rate inside the equipment, and factors such as equipment pressure, flow rate, and material viscosity need to be considered. Based on historical data, use the decision tree model to identify the key parameters that cause blockage (such as excessive pressure, low temperature, etc.), and establish a parallel extrusion blockage loss prediction model. Resource loss mainly includes waste of raw materials and energy. Use the energy efficiency evaluation model to analyze the efficiency of energy use, find out the waste links, and establish a parallel extrusion resource loss prediction model.

[0062] The first parallel extrusion simulation data is input into the above three loss prediction models. The simulation data includes all parameters related to the extrusion process, such as the temperature, pressure, flow rate, composition and fluidity of the die head, etc. According to the input data, the parallel extrusion quality loss prediction model, the blocking loss prediction model and the resource loss prediction model are run to obtain the corresponding loss coefficients respectively. Through the simulation data analysis, the quality loss prediction model gives the first parallel extrusion quality loss prediction coefficient, which reflects the degree of loss caused by quality problems under the current production conditions. For example, if the simulation data shows that the temperature is too high, it may cause the product to be insufficiently hard, and the quality loss coefficient may be 0.15, indicating that 15% of the production loss is caused by quality problems. If the simulation data shows that the pressure is too high or the fluidity is poor, it may cause equipment blockage. The blocking loss prediction model will calculate the first parallel extrusion blocking loss prediction coefficient, for example, 0.10, indicating that 10% of the production loss is caused by blocking. By analyzing the energy consumption and raw material waste in the simulation data, the resource loss prediction model will give the first parallel extrusion resource loss prediction coefficient, for example, 0.05, indicating that 5% of the production loss is caused by resource waste.

[0063] The three loss prediction coefficients (quality loss prediction coefficient, blockage loss prediction coefficient, and resource loss prediction coefficient) are combined to obtain the final first extrusion loss prediction result, which is a comprehensive evaluation that reflects the impact of all types of losses added together under the current production plan. Different weights are assigned to each loss coefficient based on the importance of different types of losses or their impact on the total cost. After combining the three loss coefficients, the final loss prediction result will be output to the loss assessment module. For example, if quality loss has a greater impact on production quality, a higher weight will be given to quality loss. By using a variety of loss prediction models, accurate predictions can be made for different types of losses, including quality loss, blockage loss, and resource waste, and production parameters can be adjusted in real time to avoid waste and equipment failure, thereby improving production efficiency and product quality.

[0064] Furthermore, step six of this application includes:

[0065] The control constraint parameters of the EPDM twin-head extrusion device are collected to construct an extrusion control constraint domain; based on the production requirements of the sealing strip, the first parallel extrusion scheme is randomly adjusted according to the extrusion control constraint domain to construct an optimization space for parallel extrusion schemes; based on the optimization space for parallel extrusion schemes, a second parallel extrusion scheme is randomly extracted; based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, a loss prediction and evaluation is performed on the second parallel extrusion scheme to obtain a second parallel extrusion loss coefficient; it is determined whether the second parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold; if the second parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold, the second parallel extrusion scheme is added to the parallel extrusion optimization strategy.

[0066] Specifically, the control constraint parameters of the EPDM twin-head extruder are obtained, that is, the parameters related to the equipment performance, process flow and production requirements, which will limit the operating space of the production process, such as temperature, pressure, speed, etc. By collecting the control constraint parameters of the EPDM twin-head extruder (such as temperature, pressure, material flow rate, etc.), an extrusion control constraint domain is established, that is, the parameter space in which extrusion can be performed within the operating range of the equipment. The extrusion control constraint domain refers to the operable range restricted by the control constraint parameters during the production process, ensuring that the equipment operates under safe and effective working conditions during the production process. The extrusion control constraint domain can be a mathematical model that describes all possible combinations of control parameters and the impact of the parameters on the extrusion process.

[0067] The production demand of sealing strips refers to the specific requirements for EPDM sealing strips during the production process, such as density, size, strength, etc. According to the production demand of sealing strips and the extrusion control constraint domain, the parameters (such as speed, temperature, pressure, etc.) in the first parallel extrusion scheme are randomly adjusted to create multiple new schemes to obtain the parallel extrusion scheme optimization space. The parallel extrusion scheme optimization space is a scheme space formed by multiple possible parallel extrusion schemes obtained by random adjustment under a given control constraint domain and production demand, that is, a collection of all possible optimization schemes, and each scheme in the space is a potential optimization scheme.

[0068] Another scheme is randomly extracted from all parallel extrusion schemes except the first parallel extrusion scheme in the parallel extrusion scheme optimization space as the second parallel extrusion scheme. Similarly, the second parallel extrusion scheme is subjected to loss prediction and evaluation through the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit to obtain the second parallel extrusion loss coefficient. The process is the same as the first parallel extrusion scheme, and no further details are given here. The randomly extracted second parallel extrusion scheme is input into the simulation unit to simulate the extrusion process, and the loss prediction is performed on the result through the extrusion loss prediction unit, and the loss result is transmitted to the loss evaluation integration unit to obtain the loss coefficient of the second parallel extrusion scheme.

[0069] Determine whether the second parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold. If it is less than the set threshold, the scheme is considered feasible and suitable for the next step. If the loss coefficient of the second parallel extrusion scheme meets the threshold requirement, the scheme is added to the final parallel extrusion optimization strategy. The parallel extrusion optimization strategy refers to a scheme that meets the loss threshold requirement, which can be selected and applied in actual production. By adjusting and optimizing the first parallel extrusion scheme, generating multiple feasible extrusion schemes, and selecting the optimal scheme through loss prediction and loss evaluation, not only the optimization efficiency of the production process is improved, but also the loss can be effectively reduced, ensuring that the production process is more efficient and has higher quality control capabilities.

[0070] Furthermore, the present application also includes the following steps:

[0071] If the second parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, the second parallel extrusion scheme is eliminated, and a third parallel extrusion scheme is randomly extracted according to the parallel extrusion scheme optimization space; based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, the third parallel extrusion scheme is subjected to loss prediction evaluation to obtain a third parallel extrusion loss coefficient; it is determined whether the third parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold; if the third parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold, the third parallel extrusion scheme is added to the parallel extrusion optimization strategy; if the third parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, the third parallel extrusion scheme is eliminated, and the parallel extrusion scheme optimization space is continued to be optimized and analyzed according to the predetermined extrusion loss threshold, the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit until the parallel extrusion optimization strategy is obtained.

[0072] Specifically, if the second parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, it means that the scheme is not suitable for production, cannot enter the final optimization strategy, and needs to be eliminated. Continue to randomly select a new extrusion scheme from the parallel extrusion scheme optimization space for evaluation. Similarly, the third parallel extrusion scheme is simulated using the parallel extrusion simulation unit to predict the performance of the scheme in actual production. Then, the loss prediction unit will evaluate the quality loss, blockage loss and resource loss of the scheme based on the simulation results. Finally, the loss evaluation integration unit weights and combines these loss results to calculate the loss coefficient of the third parallel extrusion scheme. The calculated third parallel extrusion loss coefficient is compared with the set loss threshold. If the loss coefficient is less than the threshold, it means that the scheme meets the production efficiency and quality requirements, and it is added to the parallel extrusion optimization strategy. If the loss coefficient is greater than the threshold, the scheme will be eliminated and cannot continue to enter the optimization strategy.

[0073] If the current parallel extrusion solution (either the second or third solution) does not meet the loss threshold, continue to look for other solutions in the parallel extrusion solution optimization space, and perform further optimization analysis according to the above steps until a solution that meets the requirements is found. Through iterative optimization, an extrusion solution with lower risk and meeting production needs is found, and the optimal parallel extrusion optimization strategy is constructed, which helps to improve the adaptability and flexibility of the production process, optimize production parameters, improve production efficiency and product quality, and reduce risks and losses.

[0074] In summary, the EPDM rubber sealing strip dual-head intelligent control parallel extrusion method provided in this application has the following technical effects:

[0075] By obtaining the EPDM rubber extrusion task of the EPDM double-head extruder, wherein the EPDM rubber extrusion task includes the EPDM rubber mixture corresponding to the EPDM rubber sealing strip to be produced, and the EPDM double-head extruder includes a first head extrusion component and a second head extrusion component; obtaining the sealing strip production demand corresponding to the EPDM rubber sealing strip to be produced, combining the EPDM rubber mixture, making a double-head parallel extrusion decision for the first head extrusion component and the second head extrusion component, and obtaining a first parallel extrusion plan; activating the extrusion loss prediction and evaluation module, wherein the extrusion loss prediction and evaluation module includes a parallel extrusion simulation unit, an extrusion loss prediction unit and a loss evaluation integration unit; based on the parallel extrusion The simulation unit, the extrusion loss prediction unit and the loss evaluation integrated unit perform loss prediction and evaluation on the first parallel extrusion scheme to obtain the first parallel extrusion loss coefficient; determine whether the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold; if the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integrated unit, the first parallel extrusion scheme is optimized and adjusted according to the predetermined extrusion loss threshold to generate a parallel extrusion optimization strategy; based on the parallel extrusion optimization strategy, the EPDM rubber mixture is subjected to dual-head parallel extrusion according to the first head extrusion component and the second head extrusion component. That is to say, by obtaining the EPDM rubber extrusion task, according to the production demand and the characteristics of the EPDM rubber mixture, the working scheme of the first head and the second head is made parallel extrusion decision, by simulating the parallel extrusion process, the possible loss is predicted and evaluated, the first parallel extrusion loss coefficient is obtained, and it is determined whether it is greater than or equal to the predetermined loss threshold. In the case where the loss coefficient exceeds the standard, the optimization adjustment is started, the parallel extrusion scheme is adjusted, and the dual-head extrusion system is regulated, which significantly improves the production efficiency of the EPDM rubber sealing strip during large-scale production.

[0076] 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.

[0077] 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. EPDM rubber sealing strip dual-head intelligent control parallel extrusion method, characterized in that: include: Obtaining an EPDM rubber extrusion task of an EPDM double-head extruder, wherein the EPDM rubber extrusion task includes an EPDM rubber mixture corresponding to the EPDM rubber sealing strip to be produced, and the EPDM double-head extruder includes a first head extrusion assembly and a second head extrusion assembly; Obtaining the sealing strip production demand corresponding to the EPDM rubber sealing strip to be produced, and combining the EPDM rubber mixture, making a dual-head parallel extrusion decision for the first head extrusion component and the second head extrusion component to obtain a first parallel extrusion solution; Activating an extrusion loss prediction and evaluation module, wherein the extrusion loss prediction and evaluation module includes a parallel extrusion simulation unit, an extrusion loss prediction unit, and a loss evaluation integration unit; Performing loss prediction and evaluation on the first parallel extrusion scheme based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit to obtain a first parallel extrusion loss coefficient; Determining whether the first parallel extrusion loss coefficient is greater than or equal to a predetermined extrusion loss threshold; If the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, the first parallel extrusion scheme is optimized and adjusted according to the predetermined extrusion loss threshold to generate a parallel extrusion optimization strategy; Based on the parallel extrusion optimization strategy, the EPDM rubber mixture is subjected to dual-head parallel extrusion according to the first head extrusion component and the second head extrusion component; Obtaining the sealing strip production demand corresponding to the EPDM rubber sealing strip to be produced, combining the EPDM rubber mixture, making a dual-head parallel extrusion decision for the first head extrusion assembly and the second head extrusion assembly, and obtaining a first parallel extrusion scheme, including: Collecting basic parameters of the EPDM rubber mixture to obtain rubber mixture information; Perform dual-head parallel extrusion decision learning according to the first head extrusion component and the second head extrusion component, and build a dual-head parallel extrusion decision module; Inputting the sealing strip production demand and the rubber mixture information into the dual-head parallel extrusion decision module to obtain the first parallel extrusion plan; Based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, the first parallel extrusion scheme is subjected to loss prediction evaluation to obtain a first parallel extrusion loss coefficient, including: Modeling is performed based on the EPDM twin-head extrusion device to construct a twin-head extrusion model; Based on the dual-head extrusion model and the parallel extrusion simulation unit, the EPDM rubber mixture is simulated extruded according to the first parallel extrusion scheme to obtain first parallel extrusion simulation data; Inputting the first parallel extrusion simulation data into the extrusion loss prediction unit to obtain a first extrusion loss prediction result; Inputting the first extrusion loss prediction result into the loss evaluation integration unit to generate the first parallel extrusion loss coefficient, wherein the loss evaluation integration unit includes an extrusion quality loss weight, an extrusion blockage loss weight, and an extrusion resource loss weight; If the first parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, the first parallel extrusion scheme is optimized and adjusted according to the predetermined extrusion loss threshold to generate a parallel extrusion optimization strategy, including: Collecting control constraint parameters of the EPDM twin-head extruder to construct an extrusion control constraint domain; Based on the production demand of the sealing strip, randomly adjusting the first parallel extrusion scheme according to the extrusion control constraint domain, and constructing an optimization space of parallel extrusion schemes; According to the parallel extrusion scheme optimization space, randomly extracting a second parallel extrusion scheme; Based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, performing loss prediction evaluation on the second parallel extrusion scheme to obtain a second parallel extrusion loss coefficient; Determining whether the second parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold; If the second parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold, adding the second parallel extrusion scheme to the parallel extrusion optimization strategy; The dual-head parallel extrusion decision learning is performed according to the first head extrusion component and the second head extrusion component, and a dual-head parallel extrusion decision module is built, including: Perform a dual-head parallel extrusion decision record search based on the first head extrusion component and the second head extrusion component to obtain a sealing strip production demand sample set, a rubber mixture information sample set, and a parallel extrusion solution sample set; Using the sealing strip production demand sample set and the rubber mixture information sample set as input data and the parallel extrusion scheme sample set as output data, supervised training is performed on the deep feedforward neural network, and when the number of training times meets the training number constraint, the extrusion decision loss coefficient is obtained; Determining whether the extrusion decision loss coefficient is less than an extrusion decision loss threshold; If the extrusion decision loss coefficient is less than the extrusion decision loss threshold, the dual-head parallel extrusion decision module is generated.

2. The EPDM rubber sealing strip dual-head intelligent control parallel extrusion method according to claim 1, characterized in that: Inputting the first parallel extrusion simulation data into the extrusion loss prediction unit to obtain a first extrusion loss prediction result includes: The extrusion loss prediction unit includes a parallel extrusion quality loss prediction model, a parallel extrusion blockage loss prediction model and a parallel extrusion resource loss prediction model; Inputting the first parallel extrusion simulation data into the parallel extrusion quality loss prediction model to obtain a first parallel extrusion quality loss prediction coefficient; Inputting the first parallel extrusion simulation data into the parallel extrusion blocking loss prediction model to obtain a first parallel extrusion blocking loss prediction coefficient; Inputting the first parallel extrusion simulation data into the parallel extrusion resource loss prediction model to obtain a first parallel extrusion resource loss prediction coefficient; The first parallel extrusion quality loss prediction coefficient, the first parallel extrusion congestion loss prediction coefficient and the first parallel extrusion resource loss prediction coefficient are output as the first extrusion loss prediction result.

3. The EPDM rubber sealing strip dual-head intelligent control parallel extrusion method according to claim 1, characterized in that: Determining whether the second parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold includes: If the second parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, the second parallel extrusion scheme is eliminated, and a third parallel extrusion scheme is randomly extracted according to the parallel extrusion scheme optimization space; Based on the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit, performing loss prediction evaluation on the third parallel extrusion scheme to obtain a third parallel extrusion loss coefficient; Determining whether the third parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold; If the third parallel extrusion loss coefficient is less than the predetermined extrusion loss threshold, adding the third parallel extrusion scheme to the parallel extrusion optimization strategy; If the third parallel extrusion loss coefficient is greater than or equal to the predetermined extrusion loss threshold, the third parallel extrusion scheme is eliminated, and the optimization space of the parallel extrusion scheme is continued to be optimized and analyzed according to the predetermined extrusion loss threshold, the parallel extrusion simulation unit, the extrusion loss prediction unit and the loss evaluation integration unit until the parallel extrusion optimization strategy is obtained.

4. The EPDM rubber sealing strip dual-head intelligent control parallel extrusion method according to claim 1, characterized in that: The first die extrusion assembly includes a first extruder, a second extruder and a first die; The second die extrusion assembly comprises a third extruder, a fourth extruder and a second die, wherein the first die extrusion assembly and the second die extrusion assembly share a vulcanization box.

Images