Intelligent rubber mixing prediction system and method

Abstract

The invention provides an intelligent rubber mixing prediction system and method, relates to the technical field of rubber mixing, and can improve the technical problem that the service life of rubber cannot be accurately predicted in related technologies. The prediction system is applied to a rubber mixing production line, the rubber mixing production line comprises a rubber mixing machine, and the rubber mixing machine is used for plastifying raw rubber. The prediction system comprises an acquisition module, the acquisition module is used for acquiring influence factors when the rubber mixing machine pauses rubber mixing, and the influence factors comprise one or more of equipment parameters of the rubber mixing machine and state parameters of raw rubber when the rubber mixing machine pauses rubber mixing; and the prediction module is coupled with the acquisition module, and the prediction module is used for predicting the service life of the rubber according to the influence factors.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of rubber refining technology, and in particular to an intelligent rubber refining prediction system and method. Background Art

[0002] The rubber mixing process is a key step in the production of rubber products. It involves mixing and processing raw rubber with various additives to form a uniform rubber compound with specific properties. This process is crucial to ensuring the quality, performance, and consistency of the final product.

[0003] The rubber mixer is the core equipment for realizing this process. It plasticizes the raw rubber through mechanical action and changes its physical properties, such as viscosity, elasticity and plasticity, to meet the requirements of subsequent processes such as molding and vulcanization.

[0004] In existing rubber mixing technology, the design and operation of rubber mixing mills are based on the assumption of continuous operation. This continuity helps maintain the consistency and stability of the rubber compound, thereby ensuring product quality.

[0005] However, in actual production, unexpected situations may arise, such as power outages, equipment failures, or changes in operational requirements, all of which can cause the rubber mixer to pause. Such sudden pauses not only disrupt the mixing process but can also adversely affect the rubber's physical properties and the lifespan of the final product. For example, during a pause, the temperature and chemical state of the rubber compound may change. These changes can affect the rubber's plasticization and molecular structure, and thus, its processing performance and service life. Furthermore, a pause can lead to uneven pressure distribution within the compound, affecting the rubber's physical properties.

[0006] While technologies are now capable of controlling multiple variables in the rubber mixing process, such as temperature, pressure, and chemical composition, insufficient attention has been paid to the impact of unexpected mixing mill stops on rubber life. This has led to certain deviations in rubber life prediction and quality control in actual production. Summary of the Invention

[0007] The embodiments of the present application provide an intelligent rubber refining prediction system and method, which are used to improve the technical problem in related technologies that the life of rubber cannot be accurately predicted.

[0008] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions: In a first aspect, embodiments of the present application provide an intelligent rubber mixing prediction system for use in a rubber mixing production line. A rubber mixing production line typically includes a rubber mixer, an extruder, and a vulcanizer. The rubber mixer is used to plasticize raw rubber. The rubber material processed by the rubber mixer directly enters the extruder, where it is heated and plasticized, and then extruded into the desired shape through a specific mold. The extruded rubber product immediately enters the vulcanizer for vulcanization. The vulcanization process transforms the rubber from a linear structure into a three-dimensional network structure, giving the rubber its ultimate physical properties and chemical stability.

[0009] The prediction system includes an acquisition module and a prediction module.

[0010] The acquisition module is used to acquire the influencing factors when the rubber mixer is suspended from mixing rubber. The influencing factors include one or more of the equipment parameters of the rubber mixer and the state parameters of the raw rubber when mixing rubber is suspended.

[0011] The acquisition module can acquire the aforementioned parameters through multiple sensors. For example, the acquisition module can be connected to temperature sensors, pressure sensors, timers, and other sensors installed on the rubber mixer. To ensure that the prediction system can continue to operate normally during a power outage at the rubber mixer, the prediction system and its connected sensors can be powered by a power source different from that of the rubber mixer, such as a backup power source.

[0012] The prediction module is coupled to the acquisition module, and is used to predict the service life of the rubber according to the influencing factors.

[0013] In this way, the intelligent rubber mixing prediction system in this application can predict the life of rubber when the rubber mixing machine is paused during the rubber mixing process, improving the technical problem in related technologies that the life of rubber cannot be accurately predicted.

[0014] In some implementations of the first aspect, the equipment parameters of the rubber mixer include the total pause time and the pressure of the rubber mixer on the raw rubber during the pause; the state parameters of the raw rubber include the initial temperature of the raw rubber when the rubber mixing is paused, the temperature change rate of the raw rubber, the final temperature of the raw rubber and the duration of the final temperature.

[0015] In some implementations of the first aspect, the prediction system further includes an evaluation module, which is coupled to the prediction module, and is used to evaluate the life of the rubber of each production sequence; wherein the prediction module establishes a first mapping table based on the influencing factors of each production sequence and the life of the rubber of each production sequence, and the prediction module predicts the life of the rubber of the corresponding production sequence based on the first mapping table and the influencing factors of the corresponding production sequence.

[0016] In some implementations of the first aspect, the evaluation module includes: a testing unit, a feature determination unit, and an evaluation unit. The testing unit is used to configure different test environments and test the rubber.

[0017] The testing unit can configure different testing environments for rubber and perform testing on it. For example, the testing unit can simulate the rubber's operating environment, such as a machinery factory or electronics factory, and test the rubber in the corresponding environment. It is understood that the testing unit can be a laboratory, test cabinet, or experimental equipment equipped with testing capabilities.

[0018] The feature determination unit is coupled to the test unit, and is configured to select an evaluation feature according to a test environment of the test unit. The evaluation unit is configured to evaluate the life of the rubber according to the evaluation feature.

[0019] For example, the evaluation characteristics may be multiple physical characteristics and / or chemical characteristics such as tensile strength, hardness, elongation at break, resilience, insulation resistivity, solvent resistance, etc. After the test unit configures the test environment, the characteristic determination unit selects corresponding characteristics according to the corresponding test environment.

[0020] In some implementations of the first aspect, the rubber mixer plasticizes the raw rubber according to a first strategy, and the prediction system further includes a compensation module and a control module. The compensation module is coupled to the rubber mixer and configured to generate an intermediate correction factor based on the influencing factor. The control module is coupled to the rubber mixer and further coupled to the compensation module and configured to provide the first strategy and generate a second strategy based on the first strategy and the intermediate correction factor. The rubber mixer, after pausing rubber mixing, continues plasticating the raw rubber according to the second strategy.

[0021] In some embodiments, the first strategy may include key control parameters or parameter curves during the mixing process of the rubber mixer, such as mixing time, mixing temperature, and mixing pressure. When a pause occurs, intermediate correction factors are calculated based on the acquired influencing factors. These correction factors are used to guide how to adjust the subsequent mixing process to compensate for the impact of the pause. Intermediate correction factors may include time correction factors, temperature correction factors, and pressure correction factors, respectively used to adjust the subsequent mixing time, temperature, and pressure control. These intermediate correction factors can be calculated based on the influencing factors during the mixing pause and a preset mathematical model to quantify the impact of the pause on various aspects of the mixing process (time, temperature, pressure, etc.), providing a quantitative basis for subsequent strategy adjustments.

[0022] In some implementations of the first aspect, the first strategy includes the mixing time of the rubber mixer during the mixing process; generating the correction factor based on the influencing factor includes generating the time correction factor based on the total time of the pause, the pressure on the raw rubber during the pause, the initial temperature of the raw rubber, the temperature change rate of the raw rubber, the final temperature, and the duration of the final temperature, and a first formula, wherein the first formula is: in, is the time correction factor, is the total time of the pause, The time of the entire mixing cycle (the estimated or set total mixing time under normal conditions without suspension) is The duration of the final temperature (the length of time the raw rubber temperature is maintained at or close to the final temperature during the pause period), is the final temperature of the raw rubber, is the temperature change rate (for example, the average temperature drop rate over a period of time after the pause begins, which is a positive value), is the pressure of the rubber mixer on the raw rubber (for example, the rotor pressure or cavity pressure of the kneader), It is the reference pressure during the mixing process (for example, the set pressure or average pressure during normal mixing).

[0023] and is a dimensionless weight constant, usually between 0 and 1, which is used to characterize the relative importance of the two factors, the total pause time and the final temperature holding time, to the required time correction. For example, The larger the value, the greater the influence of the total pause duration on the time correction.

[0024] and are dimensionless exponential constants that can be determined by systematic experimentation with specific rubber formulations, mixer types, and pause conditions, or by regression analysis or machine learning training based on historical production data. They characterize the relative value of the rate of temperature change ( / ) and the relative value of the pressure at the moment of pause ( / ) is sensitive to time corrections. For example, A larger value indicates a more sensitive time correction to temperature changes. The specific values of these constants depend on the rubber material properties (such as specific heat capacity and thermal conductivity), the rubber mixer model (such as thermal insulation performance and pressure control accuracy), and the specific rubber mixing process parameters. Determination methods include, but are not limited to, conducting experiments under different pause conditions, recording influencing factors and resulting changes in rubber properties (for example, lifespan as determined by the evaluation module), then developing a mathematical model and fitting the optimal constant values using methods such as minimizing prediction errors. It is understood that once these constants are determined, they can be reused with the same materials and equipment.

[0025] In some implementations of the first aspect, the first strategy includes the rubber mixing temperature during the rubber mixing process of the rubber mixer (for example, a set temperature control curve), and generating the correction factor based on the influencing factor includes generating the temperature correction factor based on the total pause time, the pressure on the raw rubber during the pause, the initial temperature of the raw rubber, the temperature change rate of the raw rubber, the final temperature, and the duration of the final temperature, and a second formula, where the second formula is: in, is the temperature correction factor, which quantifies the amount of compensation or adjustment required for temperature control in the subsequent mixing process due to the impact of the pause. The time of the entire rubber mixing cycle, is the duration of the final temperature, is the initial temperature of the raw rubber (referring to the raw rubber temperature at the moment of pause, when the rubber mixer stops working), The final temperature of the raw rubber (referring to the temperature of the raw rubber after natural cooling or insulation at the end of the pause), is the pressure of the rubber mixer on the raw rubber, is the scale for pressure changes (for example, it can be set to a constant representing the typical pressure range of the process, used to normalize the pressure to make it more universal).

[0026] β is a dimensionless exponential constant that can usually be determined experimentally or by data analysis and characterizes the relative value of the temperature change during the pause period (( ) / ) is sensitive to temperature correction. The value can be optimized through experiments and data fitting. For example, experiments are conducted under different pause times and different temperature change conditions, the influencing factors and the final rubber properties are recorded, and the optimal β value is determined by fitting. The term represents the effect of the pressure at the moment of pause on the temperature correction, and the exponent represents the use of the square root of the pressure ratio to evaluate the effect.

[0027] In some implementations of the first aspect, the first strategy includes the rubber mixing pressure of the rubber mixer during the mixing process (for example, a set pressure control curve), and generating the correction factor based on the influencing factor includes: generating the temperature correction factor based on the total pause time, the pressure on the raw rubber during the pause, the initial temperature of the raw rubber, the temperature change rate of the raw rubber, the final temperature, and the duration of the final temperature, and a third formula, wherein the third formula is: in, is the pressure correction factor, is the total time of the pause, The time of the entire rubber mixing cycle, is the initial temperature of the raw rubber, is the final temperature of the raw rubber, is the pressure of the rubber mixer on the raw rubber, It is the reference pressure in the rubber mixing process. Log represents a logarithmic function. For example, the natural logarithm (ln) or the logarithm with base 10 (log10) can be used. and is a constant.

[0028] It is a dimensionless weight constant, usually between 0 and 1, which represents the relative importance of the pause duration ratio to the pressure correction. is a dimensionless exponential constant, usually determined by experiment or data analysis, that characterizes the ratio of temperature change during the pause ( ) to the sensitivity of the pressure correction. The determination of these constants is similar to the above constants and can be optimized through systematic experiments and data fitting. For example, data are collected under different pause conditions, a mathematical model is established, and the optimal and value.

[0029] In the above formula, the time correction factor Ct, temperature correction factor Cv, and pressure correction factor Cp quantify the impact of a mixing pause on the time, temperature, and pressure conditions required for subsequent mixing. For example, if Ct > 1, it means that due to the pause, the raw rubber may require more time to undergo shearing and mixing, and subsequent mixing may take longer to achieve the desired plasticizing effect or molecular weight distribution. If Cv < 1, it means that the cooling or temperature change caused by the pause may require adjustments to the subsequent heating strategy. For example, the target temperature may need to be appropriately lowered to avoid excessive thermal degradation, or the temperature curve may need to be adjusted. If Cp > 1, it means that the pause may cause uneven pressure distribution or viscosity changes in the raw rubber. The target pressure or speed of subsequent mixing may need to be appropriately increased to apply sufficient shear force.

[0030] In some implementations of the first aspect, the prediction system further includes a feedback module, which is coupled to the control module and further coupled to the evaluation module, and is configured to generate a feedback degree of the influencing factor of the corresponding production sequence based on the life of the rubber of the corresponding production sequence and the reference life of the rubber.

[0031] The control module is used to generate a target correction factor according to the intermediate correction factor and the feedback degree, and to generate a target strategy according to the first strategy and the target correction factor. After pausing rubber mixing, the rubber mixer continues to plasticize the raw rubber according to the target strategy.

[0032] In the second aspect, an embodiment of the present application also provides a rubber mixing prediction method, which is applied to a prediction system as in any implementation method of the first aspect, wherein the rubber mixer plasticizes the raw rubber according to a production strategy, and the production strategy includes a first strategy, a second strategy and a target strategy. The method includes: obtaining an influencing factor when the rubber mixer suspends rubber mixing, and the influencing factor includes one or more of the equipment parameters of the rubber mixer and the state parameters of the raw rubber when the rubber mixing is suspended; predicting the life of the rubber according to the influencing factor; generating an intermediate correction factor according to the influencing factor; generating the second strategy according to the first strategy and the intermediate correction factor; generating a feedback degree of the influencing factor of the corresponding production sequence according to the life of the rubber and the reference life of the rubber; generating a target correction factor according to the intermediate correction factor and the feedback degree; generating a target strategy according to the first strategy and the target correction factor. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 Provides a schematic diagram of the structure of a prediction system and a rubber mixing production line for some embodiments of the present application; Figure 2 A schematic diagram of the structure of a prediction system provided in some embodiments of the present application; Figure 3 A schematic diagram of the structure of an evaluation module provided in some embodiments of the present application; Figure 4 A flowchart of a prediction method provided for some embodiments of the present application. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0035] Hereinafter, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified with "first," "second," etc., may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0036] In addition, in this application, directional terms such as "up", "down", "left", and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts. They are used for relative descriptions and clarifications, and they may change accordingly according to changes in the orientation of the components in the drawings.

[0037] In this application, unless otherwise specified or limited, the term "connection" should be understood broadly. For example, "connection" can mean fixed connection, detachable connection, or integration; it can mean direct connection or indirect connection through an intermediate medium. In addition, the term "coupling" can refer to the manner in which electrical connection is achieved for signal transmission.

[0038] As used herein, “about,” “substantially,” or “approximately” includes the stated value and reference values that are within an acceptable range of deviation from the particular value, where the acceptable range of deviation is determined by one of ordinary skill in the art taking into account the measurements in question and errors associated with the measurement of the particular quantity (i.e., limitations of the measurement system).

[0039] In the embodiments of this application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplarily" or "for example" is intended to present the relevant concepts in a concrete manner.

[0040] The rubber mixing process is a key step in the production of rubber products. It combines various raw materials and processes them into a uniform rubber compound. This process is typically performed in a rubber mixer. The mixer mechanically plasticizes the raw rubber (compound), modifying its physical properties to meet the requirements of subsequent processes.

[0041] In conventional rubber mixing technology, the mixing mill typically operates continuously to ensure the quality and properties of the rubber compound. However, in actual production, unexpected situations such as power outages, equipment failures, or changes in operational requirements may cause the mixing mill to pause. Such sudden pauses can adversely affect the processing properties of the rubber and the lifespan of the final product, leading to inaccurate predictions of the rubber's lifespan.

[0042] When a rubber mill pauses, the temperature, pressure, and chemical composition of the rubber compound may change. For example, the compound may cool during the pause, causing a drop in temperature, which can affect the plasticization and molecular structure of the rubber. Furthermore, the pause may lead to uneven pressure distribution within the compound, which in turn affects the physical properties of the rubber. Therefore, a pause in the rubber mill may shorten the service life of rubber products, rendering existing methods for predicting rubber life ineffective.

[0043] The embodiment of the present application provides an intelligent rubber mixing prediction system 200 and method for improving the technical problem in related technologies that the life of rubber cannot be accurately predicted.

[0044] like Figure 1 As shown, the rubber mixing production line 100 can generally include a rubber mixing machine 110, an extruder 120 and a vulcanizing press 130. The rubber mixing machine 110 is used for plasticating raw rubber. The rubber material after the rubber mixing machine 110 processing directly enters the extruder 120, is heated and plasticized, and is then extruded into required shape through a specific mold. The rubber product after extrusion enters the vulcanizing press 130 immediately for vulcanization. The vulcanization process transforms rubber from a linear structure into a three-dimensional network structure, giving the rubber final physical properties and chemical stability.

[0045] like Figure 2 As shown, the intelligent rubber mixing prediction system 200 is applied to the rubber mixing production line 100. The prediction system 200 may include an acquisition module 210 and a prediction module 220.

[0046] The acquisition module 210 can obtain the impact factors when the rubber mixer 110 pauses mixing. The impact factors are used to characterize parameters that affect the life of the rubber during the pause. The impact factors may include equipment parameters of the rubber mixer 110 during the pause. For example, the impact factors may include the total time the rubber mixer 110 pauses mixing (hereinafter referred to as the total pause time), the pressure applied to the raw rubber by the rubber mixer 110 during the pause, and the like.

[0047] The influencing factors may also include the state parameters of the raw rubber during the pause, such as the initial temperature of the raw rubber during the pause, the rate of temperature change of the raw rubber during the pause, the final temperature of the raw rubber during the pause, and the duration of the final temperature.

[0048] The acquisition module 210 can acquire the above parameters through a plurality of sensors. For example, the acquisition module 210 can be connected to a temperature sensor, a pressure sensor, a timer, etc. provided on the rubber mixer 110. In order to ensure that the prediction system 200 can still operate normally when the rubber mixer 110 loses power, the prediction system 200 and the sensors connected thereto can be powered by a power source different from that of the rubber mixer 110, such as a backup power source.

[0049] It is understandable that in order to more accurately evaluate the impact of suspending rubber mixing on the life of rubber, the influencing factors can also include more parameters. In light of this application, those skilled in the art can add or reduce some parameters as needed.

[0050] The prediction module 220 can be coupled to the acquisition module 210. The prediction module 220 can predict the lifespan of the rubber based on the influencing factors. For example, the prediction module 220 can monitor the influencing factors of each production sequence and the lifespan of the rubber in the corresponding sequence. It should be noted that, in order to better reflect the inventive concept of this application, the production sequence in this application refers to the production sequence in which the rubber mixer 110 has paused during the rubber mixing process.

[0051] For example, the prediction module 220 may establish a first mapping table according to the influencing factors of each production sequence and the life of the rubber of each production sequence, where the first mapping table is used to represent the mapping relationship between the influencing factors and the life of the rubber.

[0052] In this way, by establishing the first mapping table, the corresponding relationship between the influencing factors and the rubber life can be clearly obtained. After long-term data accumulation or a large amount of data testing, the mapping relationship between different influencing factors and different rubber lifespans can be obtained.

[0053] In the subsequent rubber mixing process, when the rubber mixer 110 pauses, the prediction module 220 can predict the life of the rubber produced this time by using the influencing factors obtained by the acquisition module 210 and the first mapping table, thereby improving the technical problem in the related art that the rubber life cannot be accurately predicted.

[0054] It should be noted that predicting rubber lifespan does not mean accurately determining the lifespan of the rubber. Rather, it means making a reasonable estimate of the rubber's lifespan based on past data, experience, and patterns, thereby obtaining an approximate lifespan, so that the produced rubber can be used in appropriate scenarios. Therefore, accurately predicting the rubber lifespan described in this application means making the prediction closer to the actual value.

[0055] In some embodiments, prediction system 200 further includes an evaluation module 230. Evaluation module 230 may be coupled to prediction module 220 and configured to evaluate the lifespan of the rubber in each production sequence. Prediction module 220 establishes a first mapping table based on the rubber lifespan estimated by evaluation module 230 and the influencing factors of the corresponding production sequence, and predicts the lifespan of the rubber in the corresponding production sequence based on the first mapping table and the influencing factors of the corresponding production sequence.

[0056] like Figure 3 As shown, illustratively, the evaluation module 230 may include a testing unit 231 , a feature determination unit 232 , and an evaluation unit 233 .

[0057] Testing unit 231 can configure different testing environments for rubber and perform testing on the rubber. For example, testing unit 231 can simulate the rubber's operating environment, such as a machinery factory or electronics factory, and test the rubber in the corresponding environment. It is understood that testing unit 231 can be a laboratory, test cabinet, or experimental device equipped with testing capabilities. Those skilled in the art can select the appropriate testing environment based on actual testing requirements.

[0058] The feature determination unit 232 may be coupled to the testing unit 231 . The feature determination unit 232 may select corresponding evaluation features according to the test environment configured by the testing unit 231 .

[0059] For example, the evaluation characteristics may be multiple physical characteristics and / or chemical characteristics such as tensile strength, hardness, elongation at break, resilience, insulation resistivity, solvent resistance, etc. After the testing unit 231 configures the test environment, the characteristic determination unit 232 selects corresponding characteristics according to the corresponding test environment.

[0060] Evaluation unit 233 can be coupled to feature determination unit 232. After feature determination unit 232 determines the evaluation features, evaluation unit 233 evaluates the lifespan of the rubber based on the evaluation features. It is understood that evaluating the lifespan of the rubber based on the features corresponding to the selected rubber is a technical approach that can be implemented by those skilled in the art.

[0061] In this way, the intelligent rubber mixing prediction system 200 in the present application can predict the life of rubber when the rubber mixer 110 is paused during the rubber mixing process, thereby improving the technical problem in related technologies that the life of rubber cannot be accurately predicted.

[0062] Although the related art has considered some variables in the rubber mixing process, such as temperature control, pressure regulation, and the use of additives, it has not addressed the issue of the impact of unexpected pauses in the rubber mixer 110 on the life of the rubber. Therefore, it is necessary to compensate for the impact of such pauses on the life of the rubber in order to maintain or improve the quality of the rubber product.

[0063] In some embodiments, the prediction system 200 is further configured to provide a production strategy. The production strategy may include a first strategy and a second strategy. During normal rubber mixing, the rubber mixer 110 plasticizes the raw rubber according to the first strategy. When a pause event occurs in the rubber mixer 110, the rubber mixer 110 plasticizes the raw rubber according to the second strategy after restarting.

[0064] Prediction system 200 also includes a compensation module 240 and a control module 250. Compensation module 240 is coupled to acquisition module 210. Compensation module 240 is configured to generate an intermediate correction factor based on the influencing factor. Control module 250 is coupled to rubber mixer 110 and further coupled to compensation module 240. Control module 250 can provide a first strategy and generate a second strategy based on the first strategy and the intermediate correction factor.

[0065] In some embodiments, the first strategy may include key control parameters or parameter curves during the mixing process of the rubber mixer, such as mixing time, mixing temperature, and mixing pressure. For example, the first strategy may set a total mixing time, a cavity temperature curve or set point that varies over time, a rotor speed or pressure set point that varies over time, and the like. When a pause occurs, an intermediate correction factor is calculated based on the acquired influencing factors. The correction factor is used to guide how to adjust the subsequent mixing process to compensate for the impact of the pause. The intermediate correction factors may include a time correction factor, a temperature correction factor, and a pressure correction factor, respectively used to adjust the subsequent mixing time, temperature, and pressure control. The intermediate correction factors are calculated based on the influencing factors during the mixing pause and a preset mathematical model to quantify the potential impact of the pause on various aspects of the mixing process (time, temperature, pressure, etc.) and provide a quantitative basis for subsequent strategy adjustments.

[0066] For example, the first strategy may include the mixing time of the rubber mixer 110 during the mixing process. Therefore, the intermediate correction factor may include a time correction factor. The time correction factor is used to correct the mixing time in the subsequent mixing process. Thus, generating the intermediate correction factor based on the influencing factor includes: The time correction factor is generated based on the total time of the pause, the pressure on the rubber during the pause, the initial temperature of the rubber, the temperature change rate of the rubber, the final temperature, the duration of the final temperature, and the first formula. The first formula is: in, is the time correction factor, is the total time of the pause, in seconds or minutes, The time of the entire mixing cycle (the estimated or set total mixing time under normal conditions without suspension) is in the same unit as Consistent, The duration of the final temperature (the length of time the raw rubber temperature is maintained at or close to the final temperature during the pause period), the unit is Consistent, is the final temperature of the raw rubber, is the temperature change rate (for example, the average temperature drop rate over a period of time after the pause begins, a positive value in degrees Celsius / second or Kelvin / second), is the pressure of the rubber mixer on the raw rubber (for example, the rotor pressure or cavity pressure of the kneader), The reference pressure in the mixing process (for example, the set pressure or average pressure in the normal mixing process) is in the same unit as consistent.

[0067] and It is a dimensionless weight constant, usually between 0 and 1, which is used to characterize the relative importance of the two factors, the total pause time and the final temperature holding time, to the required time correction. The larger the value, the greater the influence of the total pause duration on the time correction.

[0068] and is a dimensionless exponential constant whose value is usually determined by systematic experimentation with specific rubber formulations, mixer types, and pause conditions, or by regression analysis or machine learning training based on historical production data. For example, and The value range of can be -5 to 5. They represent the relative value of the temperature change rate ( / ) and the relative value of the pressure at the moment of pause ( / ) is sensitive to time corrections. For example, A larger value indicates a more sensitive time correction to temperature changes. The specific values of these constants depend on the rubber material properties (such as specific heat capacity and thermal conductivity), the rubber mixer model (such as thermal insulation performance and pressure control accuracy), and the specific rubber mixing process parameters. Determination methods include, but are not limited to, conducting experiments under different pause conditions, recording influencing factors and resulting changes in rubber properties (for example, lifespan as determined by the evaluation module), then developing a mathematical model and fitting the optimal constant values using methods such as minimizing prediction errors. It is understood that once these constants are determined, they can be reused with the same materials and equipment.

[0069] In the first formula, the ratio of the total pause time to the total mixing cycle time quantifies the impact of the pause on the entire mixing cycle. The ratio of the final temperature hold time to the total mixing cycle time reflects the positive contribution of maintaining the final temperature to the mixing process. The exponential ratio of the temperature drop rate to the final temperature represents the impact of the cooling rate relative to the final temperature on the mixing time requirement. Thus, the second strategy, generated from the intermediate correction factor and the first strategy, accounts for the impact of factors affecting the mixing process during the pause of the rubber mixer 110.

[0070] In this way, when the rubber mixer 110 resumes rubber mixing, the rubber mixer 110 continues to plasticize the raw rubber according to the second strategy. The subsequent rubber mixing process takes into account the impact of the rubber mixer 110 pausing on the rubber mixing, thereby realizing the correction of the rubber mixing strategy.

[0071] It is understandable that when generating the second strategy based on the first strategy and the intermediate correction factor, in some cases it is necessary to consider the rubber mixing process already in progress in the first strategy, such as the rubber mixing time. For example, when the rubber mixing machine has already mixed rubber according to the first strategy for a time exceeding a first threshold, and the total pause time does not exceed a second threshold, when generating the second strategy based on the first strategy, the rubber mixing time used in the first strategy should be the remaining rubber mixing time of the first strategy. The setting of the first and second thresholds can be determined based on the specific type of rubber, etc., and those skilled in the art can set them as needed based on the guidance of this application, and will not be detailed here.

[0072] In another exemplary embodiment, the first strategy may include the mixing temperature during the mixing process of the rubber mixer 110. Therefore, generating the intermediate correction factor according to the influencing factor may include: The temperature correction factor is generated based on the total time of the pause, the pressure on the rubber during the pause, the initial temperature of the rubber, the temperature change rate of the rubber, the final temperature, the duration of the final temperature, and the second formula. The second formula is: in, is the temperature correction factor, which quantifies the amount of compensation or adjustment required for temperature control in the subsequent mixing process due to the impact of the pause. The time of the entire rubber mixing cycle, is the duration of the final temperature, is the initial temperature of the raw rubber (referring to the raw rubber temperature at the moment of pause, when the rubber mixer stops working), The final temperature of the raw rubber (referring to the temperature of the raw rubber after natural cooling or insulation at the end of the pause), is the pressure of the rubber mixer on the raw rubber, Scale for pressure changes (for example, this can be set to a constant representing the typical pressure range of the process, used to normalize the pressure) β is a dimensionless exponential constant that can usually be determined through experiments or data analysis and is used to characterize the relative value of temperature change during the pause period (( ) / ) is sensitive to temperature correction. The value can be optimized through experiments and data fitting. For example, experiments are conducted under different pause times and different temperature change conditions, the influencing factors and the final rubber properties are recorded, and the optimal β value is determined by fitting. For example, the value range of the exponential constant β can be -10 to 10. The term represents the effect of the pressure at the moment of pause on the temperature correction, and the exponent represents the use of the square root of the pressure ratio to evaluate the effect.

[0073] In the second formula, the exponent of the difference between the initial and final temperatures represents the effect of the change from the initial to final temperature on the mixing temperature requirement, and the exponent β reflects the sensitivity to temperature changes. The square root of the initial pressure and the scale of the pressure change is used to represent the effect of pressure on the temperature correction factor.

[0074] In this way, when the rubber mixer 110 resumes rubber mixing, the rubber mixer 110 continues to plasticize the raw rubber according to the second strategy. The subsequent rubber mixing process takes into account the impact of the mixing temperature of the raw rubber during the pause of the rubber mixer 110 on the life of the rubber, thereby realizing the correction of the rubber mixing strategy and improving the technical problem in the related technology that the pause of the rubber mixer will affect the life of the rubber.

[0075] In another exemplary embodiment, the first strategy may include the mixing pressure during the mixing process of the rubber mixer 110. Therefore, generating the intermediate correction factor according to the influencing factor may include: The pressure correction factor is generated based on the total time of the pause, the pressure on the rubber during the pause, the initial temperature of the rubber, the temperature change rate of the rubber, the final temperature, the duration of the final temperature, and the third formula. The third formula is: in, is the pressure correction factor, is the total time of the pause, The time of the entire rubber mixing cycle, is the initial temperature of the raw rubber, is the final temperature of the raw rubber, is the pressure of the rubber mixer on the raw rubber, It is the reference pressure in the rubber mixing process. Log represents a logarithmic function. For example, the natural logarithm (ln) or the logarithm with base 10 (log10) can be used. and is a constant.

[0076] It is a dimensionless weight constant, usually between 0 and 1, which represents the relative importance of the pause duration ratio to the pressure correction. is a dimensionless exponential constant, usually determined by experiment or data analysis, that characterizes the ratio of temperature change during the pause ( ) to the sensitivity of the pressure correction. The determination of these constants is similar to the above constants and can be optimized through systematic experiments and data fitting. For example, data are collected under different pause conditions, a mathematical model is established, and the optimal and For example, the exponential constant α may range from -5 to 5.

[0077] In the above formula, the time correction factor Ct, the temperature correction factor C T The pressure correction factor Cp quantifies the effect of mixing pause on the time, temperature and pressure conditions required for subsequent mixing. For example, if Ct>1, it means that due to the pause, the raw rubber may need more time to be sheared and mixed, and the subsequent mixing may take longer to achieve the desired plasticizing effect or molecular weight distribution; if C T <1, indicating that the cooling or temperature change caused by the pause may require adjustment of the subsequent heating strategy. For example, the target temperature may need to be appropriately lowered to avoid excessive thermal degradation, or the temperature curve may need to be adjusted. If Cp>1, it means that the pause may cause uneven pressure distribution or viscosity changes in the raw rubber. The target pressure or speed of subsequent mixing may need to be appropriately increased to apply sufficient shear force.

[0078] In this way, by adjusting the rubber mixing process through the above formula, it can be ensured that when production is resumed after a pause, the deviation of the rubber mixing process caused by temperature, time and pressure during the pause can be compensated, thereby ensuring that the life of the rubber is not affected by the pause of the rubber mixer 110.

[0079] The first strategy typically consists of a set of predefined mixing process parameters or control curves based on the rubber formulation characteristics and desired product performance under normal (uninterrupted) production conditions. For example, the first strategy may include the total mixing time for each stage, the chamber temperature setpoint or temperature curve over time for each stage, the rotor speed setpoint or speed curve over time, and the pressure control setpoint for a specific stage. When the mixing mill is paused for some reason, the mixing process is interrupted, and the raw rubber may have changed (e.g., temperature drop, viscosity increase). When resuming production, the remaining components of the original first strategy cannot be simply continued, as the pause has already impacted the raw rubber, requiring compensatory adjustments to subsequent processes. At this point, the control module 250 receives intermediate correction factors (Ct, Cv, Cp, etc.) calculated based on the influencing factors from the compensation module 240.

[0080] The purpose of generating a second strategy based on the first strategy and the intermediate correction factor is to adjust the original strategy based on the quantitative impact of the suspension to ensure that the expected plasticizing effect and final product performance can be achieved after resuming production. For example, one or more of the following methods can be used: For example, the key control parameters corresponding to the intermediate correction factors in the first strategy are adjusted. For example, if the remaining mixing time of the first strategy is T_remain_1, the remaining mixing time of the second strategy can be set to T_remain_2 = T_remain_1 * Ct. If the target temperature of the first strategy at a certain moment is set to Temp_target_1, the target temperature can be adjusted according to C T Adjustment, for example, setting a new target temperature can be Temp_target_2=Temp_target_1*(1+K_v*(C T -1)) Or Temp_target_2=Temp_target_1+ΔTemp_v, where ΔTemp_v is based on C T The calculated temperature adjustment, for example, ΔTemp_v=K'_v*(C T -1).

[0081] Similarly, if the target pressure of the first strategy at a certain moment is set to Pres_target_1, it can be adjusted based on Cp. For example, the new target pressure can be set as Pres_target_2 = Pres_target_1 * (1 + K_p * (Cp - 1)) or Pres_target_2 = Pres_target_1 + ΔPres_p, where ΔPres_p is the pressure adjustment calculated based on Cp, for example, ΔPres_p = K'_p * (Cp - 1). Here, K_v, K'_v, K_p, and K'_p are adjustment coefficients used to adjust the actual impact of the correction factor on the strategy parameters. These adjustment coefficients can also be optimized and determined through experiments or data analysis.

[0082] Kv and Kv' are temperature adjustment coefficients, while Kp and Kp' are pressure adjustment coefficients. These coefficients are dimensionless (for multiplicative adjustments, such as 1+K∗(Factor−1)1+K∗(Factor−1)) or have corresponding physical dimensions (for additive adjustments, such as Param+K′∗(Factor−1)Param+K′∗(Factor−1)). They are used to translate changes in the intermediate correction factors Ct, Cv, and Cp into actual adjustments to the strategy parameters. The range of these adjustment coefficients can be determined through systematic experimentation and data fitting and may vary depending on the rubber formulation and mixer characteristics.

[0083] For example, multiplicative adjustment coefficients (such as Kv and Kp) can range from -100 to 100, with specific values requiring optimization based on actual processes and data. Additive adjustment coefficients (such as Kv′, Kp′, Kv′, and Kp′) can range from -100 to 100 (or other suitable ranges) with corresponding physical dimensions (e.g., °C or MPa), with specific values also requiring determination through experimentation and data optimization. Their sign depends on the relationship between the direction of change in the correction factor and the direction of adjustment of the strategy parameter. For example, if Cv is less than 1, indicating a need for temperature increase, then K_v or K'_v may need to be negative.

[0084] For example, a lookup table or mathematical model can be pre-established. Its input includes the current state of the first strategy (e.g., elapsed execution time, current parameter values), the acquired influencing factors, and the calculated intermediate correction factors. The output is the specific control parameters or adjustment values of the second strategy. The control module then looks up the table or runs the model to obtain the second strategy.

[0085] For example, the second strategy can be designed to include one or more phases, with each phase potentially requiring different adjustment ranges for control parameters. For example, a more conservative or more aggressive temperature / pressure profile can be employed during the initial pause recovery phase, followed by a gradual transition to the main mixing phase parameters adjusted based on the correction factors.

[0086] It will be appreciated that the specific method for generating the second strategy and the parameter adjustment rules (including the parameters selected for adjustment, the functional form of the adjustment, and the numerical values of the adjustment coefficients) depend on the sensitivity of the rubber formulation to pauses, the characteristics of the rubber mixer, and the desired final product quality requirements. These strategy generation rules and parameters can be determined through extensive experimentation, historical data analysis, or offline optimization using optimization algorithms (such as genetic algorithms and simulated annealing) to achieve optimal compensation effects under different pause conditions. The control module 250 sends the generated second strategy to the rubber mixer 110, instructing it to continue the plasticating process according to the new parameters and curves after the pause is resumed.

[0087] The above embodiment describes the modification of the production strategy based on the influencing factors during the pause of the rubber mixer 110. To improve the accuracy of the modification, the life of the rubber produced according to the modified production strategy can be evaluated to obtain the feedback degree of the corresponding modification factor, thereby correcting the intermediate modification factor.

[0088] In some embodiments, prediction system 200 may further include a feedback module 260. Feedback module 260 may be coupled to control module 250 and may also be coupled to evaluation module 230. Feedback module 260 is configured to generate a feedback degree for the influencing factors for a corresponding production sequence based on the lifespan of the rubber in the corresponding production sequence and the reference lifespan of the rubber. Its specific function is to receive the actual or estimated lifespan of the rubber in the production sequence produced using the second rubber mixing strategy from evaluation module 230, compare it with a preset reference lifespan, and generate a feedback degree (Z) that quantifies the effectiveness of this compensation. For example, feedback degree Z may be the ratio of the actual lifespan to the reference lifespan, or other indicators that reflect the degree of lifespan deviation.

[0089] For example, the target correction factor can be obtained according to the following formula: in, is the target correction factor, is the intermediate correction factor, and Z is the feedback degree.

[0090] When the life of the rubber of the corresponding production sequence is greater than the reference life of the rubber, the intermediate correction factor does not need to be significantly adjusted. For example, a threshold value (such as 0.95) can be set for the feedback degree Z, and the feedback correction is only started when the life is lower than the threshold value. When the life of the rubber of the corresponding production sequence is less than the reference life of the rubber, the feedback correction mechanism will adjust the intermediate correction factor or its application method to generate a target correction factor based on the potential impact of the specific intermediate correction factor on the rubber life and the feedback degree Z this time. For example, if the total pause time and temperature change are large, the calculated intermediate correction factors Ct and Cv are both greater than 1, but the life after this rubber refining is still low (Z<1), and the feedback correction may further increase Ct and Cv. T The actual application effect of the algorithm can be studied, or the formula constants for calculating Ct and CT can be adjusted so that a more adequate compensation strategy can be generated next time under similar pause conditions.

[0091] In this way, by evaluating the life of the rubber produced according to the revised production strategy, the feedback degree of the corresponding correction factor is obtained, and the correction factor is revised according to the feedback degree, thereby improving the correction accuracy of the correction factor and thus improving the life of the rubber produced according to the revised production strategy.

[0092] In the second aspect, the embodiment of the present application further provides an intelligent rubber mixing prediction method, which is applied to the prediction system in any implementation of the first aspect. The rubber mixing machine 110 plasticizes the raw rubber according to the production strategy, and the production strategy includes the first strategy, the second strategy and the target strategy. Figure 4 As shown, the prediction methods include: S100 , obtaining an influencing factor when the rubber mixer 110 suspends rubber mixing, where the influencing factor includes one or more of the equipment parameters of the rubber mixer 110 and the state parameters of the raw rubber when the rubber mixing is suspended.

[0093] The rubber mixer 110 plasticizes the raw rubber according to the first strategy generated by the control module. When the rubber mixer 110 is paused, the acquisition module 210 obtains the influencing factors through the provided sensors and feeds them back to the compensation module 240 and the evaluation module 230 .

[0094] The impact factors are a set of parameters used to quantify the potential impact of a mixing pause on the state of the raw rubber and subsequent rubber properties. These parameters include the total duration of the pause, the pressure exerted by the mixer on the raw rubber during the pause, the initial temperature of the raw rubber during the pause, the rate of temperature change during the pause, the final temperature of the raw rubber during the pause, and the duration of the final temperature. These parameters are acquired through sensors integrated with the mixer (such as temperature sensors, pressure sensors, and timers) or external sensors connected to the system.

[0095] S200. Predict the life of rubber based on influencing factors.

[0096] Prediction module 220 predicts the rubber lifespan of the current production sequence based on a pre-established first mapping table and the currently acquired influencing factors. The first mapping table stores the corresponding relationships between different influencing factor combinations and rubber lifespan. This relationship can be obtained through extensive analysis of historical production data, experimental testing (such as that performed by evaluation module 230), or a model based on rubber aging theory. It is understandable that the influencing factors will vary for each production sequence when a pause occurs. Prediction module 220 predicts the rubber lifespan based on the current influencing factors by searching or calculating this mapping relationship.

[0097] S300: Generate an intermediate correction factor according to the influencing factor.

[0098] Compensation module 240 generates intermediate correction factors (Ct, Cv, Cp, etc.) based on the acquired influencing factors and pre-set formulas. During the calculation process, constants (such as Wpause, Whold, θτ, θp, β, Wt, α, Pscale, and Pref) previously determined through systematic experiments, data analysis, and model fitting are used. These intermediate correction factors quantify the compensation required for pauses in mixing time, temperature, and pressure.

[0099] S400: Generate a second strategy according to the first strategy and the intermediate correction factor.

[0100] After receiving the intermediate correction factor calculated by the compensation module 240, the control module 250 combines the parameters of the first strategy (normal mixing strategy) (e.g., remaining time, target temperature / pressure curve) with the intermediate correction factor according to preset strategy generation rules (e.g., applying the intermediate correction factor to the parameters of the first strategy) to generate a second strategy. This generated second strategy is used to guide the rubber mixer on how to resume mixing after resuming a pause, thereby minimizing the impact of the pause on final product performance.

[0101] S500: Generate feedback degrees of influencing factors of the corresponding production sequence according to the life of the rubber of the corresponding production sequence and the reference life of the rubber.

[0102] Evaluation module 230 evaluates the performance of the rubber produced in this production sequence using the second rubber mixing strategy, obtaining its actual or estimated lifespan. Feedback module 260 compares this lifespan with a reference lifespan for the rubber and generates a feedback degree Z using a pre-defined calculation method, for example, Z = actual lifespan / reference lifespan. Feedback degree Z reflects the degree to which the final product lifespan matches the expected standard after the second strategy has been implemented to compensate for the impact of the suspension.

[0103] S600: Generate a target correction factor according to the intermediate correction factor and the feedback degree.

[0104] Control module 250 combines the intermediate correction factors and the feedback degree Z to generate a target correction factor (CM) based on a pre-defined feedback correction mechanism (e.g., adjusting formula constants or the application of the intermediate correction factors). For example, feedback degree Z can be used to adjust the constants used to calculate the intermediate correction factors, or a learning algorithm can be used to map the intermediate correction factors and feedback degree to the target correction factor to achieve more accurate correction.

[0105] S700: Generate a target strategy according to the first strategy and the target correction factor.

[0106] Based on the first strategy and the target correction factor after feedback correction, the control module 250 generates a final rubber mixing strategy, referred to as the target strategy, used to guide the rubber mixer to resume production. The target strategy is generated similarly to the second strategy, but the intermediate correction factors are replaced with the target correction factors, or the target correction factors are used to fine-tune the second strategy. After resuming from a pause, the rubber mixer 110 will continue mixing according to this finalized target strategy.

[0107] Through the description of the above embodiments, those skilled in the art will clearly understand that the diagnostic methods in the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred implementation method. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the relevant art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, or optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0108] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0110] Units described as separate components may or may not be physically separate, and components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0111] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware.

[0112] The above content is only a specific embodiment of this application, but the scope of protection of this application is not limited to this. Any changes or replacements within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An intelligent rubber mixing prediction system is applied to a rubber mixing production line, wherein the rubber mixing production line includes a rubber mixing machine, and the rubber mixing machine is used to plasticate raw rubber, characterized in that: The prediction system includes: An acquisition module, the acquisition module is used to obtain an influencing factor when the rubber mixer pauses mixing, the influencing factor including one or more of an equipment parameter of the rubber mixer and a state parameter of the raw rubber when mixing is paused; A prediction module is coupled to the acquisition module and is used to predict the service life of the rubber according to the influencing factors.

2. The prediction system according to claim 1, characterized in that The equipment parameters of the rubber mixer include the total pause time and the pressure of the rubber mixer on the raw rubber during the pause; the state parameters of the raw rubber include the initial temperature of the raw rubber during the pause, the temperature change rate of the raw rubber, the final temperature of the raw rubber and the duration of the final temperature.

3. The prediction system according to claim 2, characterized in that The prediction system further includes an evaluation module coupled to the prediction module, the evaluation module being configured to evaluate the life of the rubber of each production sequence; The prediction module establishes a first mapping table according to the influencing factors of each production sequence and the life of the rubber of each production sequence, and predicts the life of the rubber of the corresponding production sequence according to the first mapping table and the influencing factors of the corresponding production sequence.

4. The prediction system according to claim 3, characterized in that The evaluation module includes: A testing unit, which is used to configure different testing environments and test the rubber; a feature determination unit, the feature determination unit being coupled to the test unit and configured to select an evaluation feature according to a test environment of the test unit; and an evaluation unit for evaluating the life of the rubber according to the evaluation characteristics.

5. The prediction system according to claim 3, characterized in that The rubber mixer plasticizes the raw rubber according to the first strategy, and the prediction system further includes: a compensation module, coupled to the acquisition module, configured to generate an intermediate correction factor according to the influencing factor; a control module coupled to the rubber mixer and further coupled to the compensation module, the control module being configured to provide the first strategy and generate a second strategy based on the first strategy and the intermediate correction factor; Wherein, after suspending rubber mixing, the rubber mixing machine continues to plasticate the raw rubber according to the second strategy.

6. The prediction system according to claim 5, characterized in that The first strategy includes the mixing time of the rubber mixer during the mixing process; The influencing factor generates an intermediate correction factor including: A time correction factor is generated according to the total time of the pause, the pressure on the raw rubber during the pause, the initial temperature of the raw rubber, the temperature change rate of the raw rubber, the final temperature, the duration of the final temperature, and a first formula, wherein the first formula is: in, is the time correction factor, is the total time of the pause, The time of the entire rubber mixing cycle, is the duration of the final temperature, is the final temperature of the raw rubber, is the temperature change rate, is the pressure of the rubber mixer on the raw rubber, is the reference pressure during the rubber mixing process, 、 、 、 is a constant.

7. The prediction system according to claim 5, characterized in that The first strategy includes the mixing temperature of the rubber mixer during the mixing process, and the influencing factors for generating the intermediate correction factors include: A temperature correction factor is generated according to the total time of the pause, the pressure on the raw rubber during the pause, the initial temperature of the raw rubber, the temperature change rate of the raw rubber, the final temperature, the duration of the final temperature, and a second formula, wherein the second formula is: in, is the temperature correction factor, The time of the entire rubber mixing cycle, is the duration of the final temperature, is the initial temperature of the raw rubber, is the final temperature of the raw rubber, is the pressure of the rubber mixer on the raw rubber, is the scale of pressure change, is a constant.

8. The prediction system according to claim 5, characterized in that The first strategy includes the mixing pressure of the rubber mixer during the mixing process, and the influencing factors for generating the intermediate correction factors include: A pressure correction factor is generated according to the total time of the pause, the pressure on the raw rubber during the pause, the initial temperature of the raw rubber, the temperature change rate of the raw rubber, the final temperature, the duration of the final temperature, and a third formula. The third formula is: in, is the pressure correction factor, is the total time of the pause, The time of the entire rubber mixing cycle, is the initial temperature of the raw rubber, is the final temperature of the raw rubber, is the pressure of the rubber mixer on the raw rubber, is the reference pressure during the rubber mixing process, and is a constant.

9. The intelligent rubber mixing prediction system according to any one of claims 5 to 8, characterized in that: The prediction system further includes a feedback module, the feedback module being coupled to the control module and the evaluation module, and configured to generate a feedback degree of the influencing factor of the corresponding production sequence based on the life of the rubber of the corresponding production sequence and the reference life of the rubber; The control module is used to generate a target correction factor according to the intermediate correction factor and the feedback degree, and to generate a target strategy according to the first strategy and the target correction factor. After pausing rubber mixing, the rubber mixer continues to plasticize the raw rubber according to the target strategy.

10. A rubber mixing prediction method, applied to the prediction system according to any one of claims 1 to 9, characterized in that: The rubber mixer plasticizes the raw rubber according to a production strategy, wherein the production strategy includes a first strategy, a second strategy, and a target strategy. The method includes: Obtaining an influencing factor when the rubber mixer is paused, wherein the influencing factor includes one or more of an equipment parameter of the rubber mixer and a state parameter of the raw rubber when the rubber mixer is paused; Predicting the life of the rubber based on the influencing factors; generating an intermediate correction factor based on the influencing factor; generating the second strategy according to the first strategy and the intermediate correction factor; generating a feedback degree of the influencing factor of the corresponding production sequence according to the life of the rubber of the corresponding production sequence and the reference life of the rubber; generating a target correction factor according to the intermediate correction factor and the feedback degree; A target strategy is generated according to the first strategy and the target correction factor.

Images