New energy vehicle low energy consumption zoned tread tire

Abstract

The present application relates to the field of glue compound process coordination control technology in the manufacturing process of zoned tread tire, especially to the low energy consumption zoned tread tire of new energy vehicle, the crown rubber of tire tread is divided into central area S1, two side shoulder area S2 and lower bottom glue S3 along the width direction, which are made of rubber composite materials with different properties. The tire is controlled to manufacture by a coordination control system, which receives instructions defining performance gradient targets and real-time process data of the production line, processes and outputs coordination control instructions through a pre-built mapping relationship model, drives each execution mechanism, so that the interface bonding strength and material performance distribution of the co-extruded compound rubber reach the preset target, thereby maintaining wet ground grip while stably achieving low rolling resistance, solving the problem of inconsistent performance of zoned tread and unstable rolling resistance effect.

Description

Technical Field

[0001] This invention relates to the field of collaborative control technology of rubber compounding process in the manufacturing process of partitioned tread tires, and particularly to low-energy-consumption partitioned tread tires for new energy vehicles. Background Technology

[0002] With the rapid development of the new energy vehicle industry, the market has placed higher demands on tire performance. To simultaneously improve vehicle range and driving safety, tires need to provide excellent wet grip while maintaining low rolling resistance. A single-compound tread compound cannot adequately address these conflicting performance indicators.

[0003] Advances in materials science have led to the development of segmented tread tire design. In segmented tread tires, the tread is divided into multiple functional zones along its width, each using a different rubber composite material. The central zone typically prioritizes wet grip, while the shoulder zone focuses on reducing rolling resistance, and a transition layer is laid at the bottom for structural stability. Theoretically, segmented tread design can overcome the performance limitations of existing single-layer tread compounds.

[0004] However, translating the partitioned design concept into a stable and uniformly high-quality physical product presents manufacturing challenges. Partitioned tread tires involve at least three rubber compounds with different rheological properties and vulcanization behaviors, which must undergo co-extrusion, compounding, and vulcanization within a confined space. If process parameters such as rubber compound delivery, temperature, and pressure are not accurately controlled, it can easily lead to poor interfacial bonding between different rubber compounds, or deviation of the material property distribution in the finished product from the design gradient. In particular, insufficient interfacial bonding strength or substandard performance gradients directly affect the energy loss performance of the tire during dynamic use, making it impossible to consistently achieve the low rolling resistance design target, thus impacting the energy economy of new energy vehicles. Existing tire production lines generally lack the precise and coordinated control capabilities for such complex rubber compounding processes, becoming a key bottleneck restricting the mass production and performance consistency of high-performance partitioned tread tires. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a low-energy-consumption zoned tread tire for new energy vehicles. This invention solves the technical problem that the lack of precise and coordinated control over the zoned tread rubber compounding process in existing tire production lines results in substandard bonding strength and preset performance gradients between rubber compounds in different zones, ultimately leading to unstable actual rolling resistance reduction in new energy vehicle tires.

[0006] To solve the above-mentioned technical problems, the specific contents of the present invention are as follows: This invention provides a low-energy-consumption partitioned tread tire for new energy vehicles, comprising a tread having a driving surface formed by a crown rubber, wherein the crown rubber is divided along the tire width direction into a central region S1, two shoulder regions S2 located on both sides of the central region S1, and a base rubber layer S3 laid below the central region S1 and the shoulder regions S2, characterized in that... The crown rubber in the central region S1, the crown rubber in the shoulder region S2, and the base rubber S3 are made of three different rubber composite materials. The tire is manufactured according to a collaborative control command output by a collaborative control system, so that the interfacial bonding strength and material property distribution between the co-extruded composite materials in the central region S1, the shoulder region S2, and the base rubber S3 reach the target relationship defined by the preset performance gradient command. The collaborative control command is obtained by the collaborative control system based on the preset performance gradient command and real-time process parameter data from the tire production line, through a performance gradient and process parameter mapping relationship model, and distributed to multiple actuators processing the rubber materials.

[0007] Furthermore, in the low-energy-consumption zoned tread tire for new energy vehicles described in this invention, the performance gradient and process parameter mapping relationship model is obtained through the following method: Collect historical production data, which includes multiple sets of historical process parameter combinations, as well as measured data on the performance gradient of the zoned rubber compound in the finished tire corresponding to each set of historical process parameter combinations. The historical production data is used to train the model, generating a performance gradient and process parameter mapping model that reflects the correspondence between the combination of process parameters and the performance gradient of the zoned rubber compound.

[0008] Furthermore, in the manufacturing process of the low-energy-consumption zoned tread tire for new energy vehicles described in this invention, the collaborative control system also compares the current performance gradient reflected by the real-time process parameter data with the preset performance gradient command to obtain the comparison result, and corrects the collaborative control command based on the comparison result.

[0009] Furthermore, in the new energy vehicle low-energy consumption zoned tread tire of the present invention, the real-time process parameter data is synchronously collected through a sensor network deployed on the tire production line and time-series aligned based on timestamps, including temperature data, pressure data and flow rate data of the central region S1 rubber compound, the shoulder region S2 rubber compound and the base rubber compound S3 rubber compound during the co-extrusion compounding process.

[0010] Furthermore, in the manufacturing process of the low-energy-consumption zoned tread tire for new energy vehicles described in this invention, the collaborative control system also uses an optimization algorithm to optimize the initial collaborative control command output by the performance gradient and process parameter mapping relationship model. The optimization algorithm aims to maximize the interface bonding strength while minimizing the deviation of the rolling resistance coefficient of the finished tire from the preset performance gradient command.

[0011] Furthermore, in the manufacturing process of the low-energy-consumption zoned tread tire for new energy vehicles described in this invention, the collaborative control system also performs feedforward adjustments based on a digital twin model. The digital twin model simulates the compounding process of the adhesive in virtual space based on the preset performance gradient command and the cooperative control command, and predicts the virtual interface bonding strength and virtual material property distribution. The collaborative control system adjusts the collaborative control commands based on the prediction results.

[0012] Furthermore, in the new energy vehicle low-energy consumption zoned tread tire of the present invention, the comparison result is the deviation value between the current performance gradient and the preset performance gradient command; The collaborative control system has a pre-set deviation and compensation rule library. The collaborative control system queries the deviation and compensation rule library according to the deviation value to obtain the corresponding process parameter compensation amount, and generates a corrected collaborative control command based on the process parameter compensation amount.

[0013] Furthermore, in the new energy vehicle low-energy consumption zoned tread tire of the present invention, the preset performance gradient instruction defines that the first hysteresis loss of the tread rubber in the central region S1 at 0°C is greater than the second hysteresis loss of the tread rubber in the shoulder region S2 at 60°C.

[0014] Furthermore, in the new energy vehicle low-energy consumption zoned tread tire of the present invention, the preset performance gradient instruction further defines that the absolute value of the difference between the 10% secant modulus of the base rubber S3 at 23°C and the modulus of the crown rubber in the central region S1 does not exceed 10%, and the absolute value of the difference between the hysteresis loss at 60°C and the hysteresis loss of the crown rubber in the shoulder region S2 does not exceed 15%.

[0015] Furthermore, in the new energy vehicle low-energy consumption zoned tread tire of the present invention, the plurality of actuators include a first rubber extrusion mechanism, a second rubber extrusion mechanism, a third rubber extrusion mechanism, a composite mold temperature control mechanism, and a pressure application mechanism; The coordinated control commands include independent flow rate and temperature commands sent to the first rubber extrusion mechanism, the second rubber extrusion mechanism, and the third rubber extrusion mechanism, respectively, as well as temperature and pressure commands sent to the composite mold temperature control mechanism and the pressure application mechanism.

[0016] Beneficial effects of this invention: This invention employs a collaborative control system driven by a performance gradient and process parameter mapping model, a digital twin model, and a deviation and compensation rule base. Based on preset performance gradient commands and real-time process parameter data, it generates and dynamically optimizes collaborative control commands to precisely control the co-extrusion compounding process of three different rubber compounds. This ensures that the interfacial bonding strength and material property distribution of the tire's partitioned rubber compounds stably meet preset targets, directly improving the consistency of performance in partitioned tread tire products. Because the material property gradient is accurately reproduced, the high hysteresis loss characteristics of the rubber compound in the central region and the low hysteresis loss characteristics of the rubber compound in the shoulder region are stably achieved, enabling the tire to simultaneously and stably obtain excellent wet grip and low rolling resistance performance. The feedforward adjustment mechanism in the collaborative control system is based on the prediction and advance compensation of process deviations using the digital twin model, while the feedback correction mechanism dynamically responds to process disturbances through real-time performance estimation and rule base queries. The combination of these two mechanisms makes the manufacturing process insensitive to rubber compound fluctuations and environmental interference, thus ensuring the stability of the low rolling resistance effect in mass production. This effectively solves the performance inconsistency problem caused by the lack of precise collaborative control mentioned in the background art, ultimately enabling new energy vehicles equipped with this tire to achieve more reliable low-energy consumption performance. Attached Figure Description

[0017] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on the drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the structure of the low-energy-consumption zoned tread tire for new energy vehicles according to the present invention. Detailed Implementation

[0019] To make the technical solution of the present invention clearer, the present invention will be clearly and completely described below with reference to specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. The various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. To better understand the purpose of the present invention, the present invention will be described in further detail below.

[0020] Please see Figure 1 The present invention provides a low-energy-consumption partitioned tread tire for new energy vehicles. In this embodiment, the tire tread has a driving surface formed by a crown rubber. The crown rubber is divided along the tire width into a central region S1, two shoulder regions S2 located on either side of the central region S1, and a base rubber layer S3 laid beneath the central region S1 and the shoulder regions S2. The crown rubber of the central region S1, the crown rubber of the shoulder regions S2, and the base rubber S3 are made of three rubber composite materials with different physical properties. The crown rubber of the central region S1 exhibits high hysteresis loss at 0 degrees Celsius to provide excellent wet grip performance. The crown rubber of the shoulder regions S2 exhibits low hysteresis loss at 60 degrees Celsius to optimize rolling resistance. The base rubber S3 has a 10% secant modulus at 23 degrees Celsius similar to that of the crown rubber in the central region S1, and a hysteresis loss at 60 degrees Celsius similar to that of the crown rubber in the shoulder regions S2, serving as a performance transition and structural support. The differences in DIN abrasion index and hardness between the S1 tread rubber in the center area and the S2 tread rubber in the shoulder area are controlled within a small range to avoid abnormal wear and ensure driving stability.

[0021] To achieve the aforementioned zoned tread structure and ensure consistent performance, the tire is manufactured based on collaborative control commands output by a collaborative control system. The manufacturing process begins with the generation and input of preset performance gradient commands. These preset performance gradient commands are a structured set of data that clearly defines the target state to be achieved after co-extrusion compounding. This includes the interfacial bonding strength thresholds between the central region S1 rubber compound, the shoulder region S2 rubber compound, and the base rubber compound S3, as well as the material property distribution targets such as the magnitude of hysteresis loss and modulus similarity among the rubber compounds in each region at specific temperatures. The preset performance gradient commands serve as the benchmark for the operation of the collaborative control system.

[0022] At the co-extrusion compounding station of the tire production line, a sensor network is deployed to synchronously collect real-time process parameter data. This real-time process parameter data is a multi-dimensional set of process variables, specifically including three temperature data points, three pressure data points, and three flow rate data points corresponding to the S1 compound in the central region, the S2 compound in the tire shoulder region, and the S3 compound in the base compound, respectively. The temperature data reflects the actual temperature of the compound at the extruder head and the compounding die inlet; the pressure data characterizes the resistance of the compound through a specific flow channel; and the flow rate data is related to the screw speed of the extruder, collectively describing the rheological state and convergence conditions of the compound at the moment of compounding. This data is transmitted to the collaborative control system via a fieldbus.

[0023] The core of the collaborative control system is the performance gradient-process parameter mapping model. This model is a nonlinear regression model trained using machine learning methods, establishing a mapping relationship between the process parameter space and the tire performance gradient space. Model training relies on historical production data. This historical production data is a structured dataset collected from past production batches. Each data record contains a set of historical process parameter combinations, along with measured data on the zoned rubber compound performance gradients of the finished tires actually produced under those process parameters, obtained through laboratory testing. The historical process parameter combinations are the set of temperature, pressure, and flow rate data collected at that time; the measured performance gradient data include the measured values ​​of interfacial bonding strength, hysteresis loss in each region, and modulus of the corresponding tire sample. By training on a large amount of historical production data, the model can learn how adjustments to process parameters affect the final tire's performance gradient distribution.

[0024] During the manufacturing process, the collaborative control system executes online decisions. The system receives preset performance gradient commands and real-time acquired process parameter data, inputting both types of data into a performance gradient-process parameter mapping model. The model first performs forward inference, predicting the performance gradient result under the current state based on the real-time process parameter data. Subsequently, the model compares the prediction result with the objective defined by the preset performance gradient commands, internally performing calculations through an optimization algorithm. The optimization algorithm starts with the initial collaborative control commands predicted by the model and searches for the optimal solution iteratively. The objective function of the optimization algorithm is constructed in a multi-objective form. The primary sub-objective is to maximize the predicted interface bonding strength under constraints, and the secondary sub-objective is to minimize the deviation of the predicted rolling resistance coefficient of the finished tire from the target value in the command. After solving this optimization problem, the model outputs a set of optimized collaborative control commands.

[0025] To further improve control accuracy, the collaborative control system integrates a digital twin model for feedforward adjustment. Before issuing collaborative control commands to the physical actuators, the system first inputs the preset performance gradient commands and the calculated collaborative control commands into the digital twin model. The digital twin model is a virtual tire manufacturing simulation model built based on finite element analysis and rheological principles. After receiving the commands, the model simulates the co-extrusion, fusion, and cooling processes of three rubber compounds in a mold in a high-fidelity virtual space. The simulation output includes the predicted virtual interface bonding strength and virtual material property distribution. The collaborative control system compares the virtual simulation results with the preset targets. If the prediction shows a deviation trend, the system performs feedforward compensation adjustments on the upcoming collaborative control commands based on the predicted deviation, correcting potential errors in advance.

[0026] The collaborative control system also possesses closed-loop feedback correction capabilities. The system inputs real-time process parameter data into a simplified real-time performance estimator to calculate the real-time performance gradient corresponding to the current manufacturing process. The system then compares this estimated real-time performance gradient with preset performance gradient commands online to obtain the performance deviation value. The collaborative control system has a pre-built deviation-compensation rule library, which defines the corresponding process parameter compensation amounts for different performance deviation ranges. The system queries this rule library based on the calculated performance deviation value to obtain specific temperature compensation, pressure compensation, or flow rate compensation. Subsequently, the system dynamically corrects the collaborative control commands output from the master model based on these compensation amounts, generating corrected collaborative control commands to cope with instantaneous disturbances in the production process.

[0027] Ultimately, the coordinated control commands, or modified coordinated control commands, are distributed to multiple physical actuators on the production line. These actuators include the first, second, and third screw extruders responsible for the central S1 compound, the shoulder S2 compound, and the base S3 compound, respectively; a temperature control mechanism surrounding the composite die; and a pressure application mechanism providing the composite pressure. The coordinated control commands specifically include independent speed and barrel temperature settings sent to the three screw extruders, temperature settings for each zone of the die sent to the composite die temperature control mechanism, and pressure settings sent to the pressure application mechanism. These actuators precisely adjust their operating states based on the received command values, thereby controlling the delivery, temperature, mixing pressure, and composite environment of the three compounds, ensuring that the interfacial bonding strength and material property distribution of the co-extruded compound actually achieve the target relationship defined by the preset performance gradient command. Through this closed-loop process of perception, decision-making, execution, and optimization, the manufactured low-energy-consumption zoned tread tires for new energy vehicles can stably possess the designed zoned performance gradient, thus achieving a stable low rolling resistance effect while ensuring wet grip.

[0028] Embodiment 1 of the present invention: This embodiment provides a low-energy-consumption partitioned tread tire for new energy vehicles. The tire tread has a driving surface formed by a crown rubber. The crown rubber is divided into three distinct physical regions along the tire width direction. The central region S1 is located at the center of the tire tread, and its lateral width L is 65% of the total tire tread width W. Located on both sides of the central region S1 are two shoulder regions S2. The cross-sectional shape of the central region S1 is designed as a trapezoid, with 45-degree inclined overlapping surfaces on both sides to achieve a tight overlap with the shoulder regions S2. The shoulder regions S2 overlap the central region S1, and both have the same thickness. Below the central region S1 and the two shoulder regions S2, a base rubber layer S3 is laid, with a thickness of 2 mm. The crown rubber of the central region S1, the crown rubber of the shoulder regions S2, and the base rubber S3 are made of three rubber composite materials with different formulations. The center zone S1 tread rubber exhibits a hysteresis loss of 0.75 at 0°C and a 10% secant modulus of elasticity of 0.5 MPa at 23°C. The shoulder zone S2 tread rubber exhibits a hysteresis loss of 0.065 at 60°C and a 10% secant modulus of elasticity of 0.3 MPa at 23°C. The base rubber S3 exhibits a 10% secant modulus of elasticity of 0.48 MPa at 23°C and a hysteresis loss of 0.068 at 60°C. The DIN abrasion index difference between the center zone S1 tread rubber and the shoulder zone S2 tread rubber is 5, and the hardness difference is 2 Shore A hardness units. Through the above-mentioned zoned structural design and material performance matching, this tire achieves EU label A level wet grip performance and B level rolling resistance coefficient in laboratory tests, achieving a balance between wet grip performance and low rolling resistance.

[0029] Embodiment Two of the present invention: Based on the tire product provided in Embodiment One, this embodiment further details a collaborative control system and method used in its manufacturing process. A preset performance gradient instruction is specified as a structured data table. This instruction explicitly requires that in the finished tire, the hysteresis loss of the central region S1 rubber compound at 0 degrees Celsius must be greater than 0.7, the hysteresis loss of the shoulder region S2 rubber compound at 60 degrees Celsius must be less than 0.07, and the modulus of the base rubber S3 at 23 degrees Celsius must not differ from the modulus of the central region S1 rubber compound by more than 10%, and the hysteresis loss at 60 degrees Celsius must not differ from the hysteresis loss of the shoulder region S2 rubber compound by more than 15%. The instruction also sets a minimum threshold value of 15 MPa for the interfacial bonding strength. At the co-extrusion compounding station of the tire production line, non-contact infrared thermometers, melt pressure sensors, and high-precision gear pump flow meters are installed for the central region S1 rubber compound, the shoulder region S2 rubber compound, and the base rubber S3 rubber compound, respectively, forming a sensor network. The sensor network synchronously collects temperature, pressure, and flow rate data of three rubber materials at a frequency of 10 times per second. The synchronously collected temperature, pressure, and flow rate data of the three rubber materials are time-series aligned based on a unified device timestamp. The aligned temperature, pressure, and flow rate data are transformed into structured multi-dimensional feature vectors as real-time process parameter data and sent to the central processing unit of the collaborative control system via industrial Ethernet.

[0030] The performance gradient mapping model employs a deep neural network structure, with training data derived from historical production data of 500 batches from the factory over the past year. Each historical production data record contains a complete set of process parameters, namely, the temperature, pressure, and flow rate data collected during the production of the corresponding batch, as well as the measured performance gradient data obtained after destructive testing of sampled tires from that batch, including the measured interfacial bonding strength, hysteresis loss, and modulus of the rubber compound in each region.

[0031] To achieve accurate mapping from the process parameter space to the tire performance gradient space, the specific structure and training process of the deep neural network are as follows: Model Structure Configuration: The deep neural network structure includes an input layer, multiple hidden layers, and an output layer. The number of nodes in the input layer matches the dimension of the input data. Specifically, it is configured to receive a structured vector containing temperature, pressure, and flow rate data for the central region S1, the shoulder region S2, and the base rubber S3, as well as preset performance gradient command indicators. The nodes in the output layer are configured to output a collaborative control command vector, including the speed and temperature settings of the independent screw extruder and the temperature and pressure settings of the composite die. The input layer, hidden layers, and output layer adopt a fully connected network topology. Nodes in adjacent network layers are connected through a weight parameter matrix, and the nodes in the hidden layer all use the ReLU activation function for nonlinear feature mapping.

[0032] Model training steps: Data preprocessing: The collected historical process parameter combinations and performance gradient measured data are subjected to maximum and minimum value normalization processing to map the values ​​of all input and output variables to a preset dimensionless interval in order to eliminate the dimensional influence between heterogeneous data.

[0033] Loss function construction: A loss function is established based on the mean square error (MSE) between the cooperative control commands predicted by the network and the actual process parameter combinations recorded in historical production data. A regularization penalty term with respect to the preset performance gradient deviation is introduced into the loss function to constrain the goal of maximizing the interface bonding strength.

[0034] Parameter optimization algorithm: The adaptive moment estimation (Adam) optimization algorithm is used to update the network parameters through backpropagation.

[0035] Hyperparameter settings and iteration: The initial learning rate is set to 0.001, and the batch size is set to 32. During training, the network weights and bias parameters are iteratively updated according to the set loss function until the value of the loss function converges to less than the preset error threshold or reaches the preset maximum number of iterations. The training process ends, the network node connection weights are fixed, and the training completed performance gradient and process parameter mapping model is output.

[0036] After model training, it is deployed on the industrial server of the collaborative control system. During actual manufacturing, the central processing unit receives preset performance gradient instructions from the human-machine interface and real-time process parameter data from sensors, and inputs these two sets of data into the deployed mapping model. The model performs forward calculations and outputs a preliminary set of collaborative control instructions. These instructions include screw speed setpoints and temperature setpoints for each section sent to the three independent screw extruders, as well as temperature setpoints for the circulating hot oil system of the composite die and pressure setpoints for the hydraulic system. The instruction distribution unit sends these setpoint instructions to the corresponding actuators, driving the extruders, temperature control system, and pressure system to work together to begin the co-extrusion composite process of the tire crown.

[0037] Embodiment 3 of the present invention: Based on Embodiment 2, this embodiment enhances the functionality of the collaborative control system by introducing predictive feedforward and dynamic closed-loop correction mechanisms. After the mapping relationship model outputs the initial collaborative control commands, the system does not immediately issue commands. The system first inputs the preset performance gradient command and the calculated initial collaborative control command into a pre-constructed digital twin model. The digital twin model is a virtual manufacturing system established based on coupled simulation of computational fluid dynamics and solid mechanics. Its virtual scene accurately reproduces the geometry, flow channel dimensions, and thermal boundary conditions of the physical production line. After receiving the commands, the digital twin model simulates the co-extrusion, merging, fusion, and initial cooling process of three different rheological properties of rubber materials under set process parameters in virtual space. The simulation operation lasts for about 30 seconds, outputting a predicted virtual interface bonding strength of 16.5 MPa and predicting the virtual material property distribution. The collaborative control system compares the simulated predicted virtual interface bonding strength of 16.5 MPa with the command target value of 15 MPa, and compares the virtual material property distribution with the target relationship in the preset performance gradient command. Based on the slight prediction deviation generated by the comparison, the system adjusts the mold temperature setpoint in the initial collaborative control command by +2 degrees Celsius feedforward compensation, thus forming the adjusted collaborative control command.

[0038] While the physical actuators produce according to the adjusted instructions, the collaborative control system continuously runs a simplified real-time performance estimator. This estimator takes the latest real-time process parameter data as input and quickly estimates the real-time performance gradient of the tire segment being manufactured at the current moment through a lightweight regression model. The system compares this estimated real-time performance gradient with the preset performance gradient instructions online to obtain a real-time performance deviation value. The collaborative control system maintains a deviation-compensation rule base, which defines the process parameter compensation amounts corresponding to different performance deviation intervals in the form of lookup tables. For example, when the real-time estimated hysteresis loss of the S2 rubber compound in the tire shoulder region at 60 degrees Celsius is higher than the target value of 0.005, the rule base indicates that a -3 degree Celsius compensation needs to be applied to the metering section temperature setpoint of the second screw extruder. The system queries the rule base based on the currently calculated deviation value to obtain the corresponding temperature and pressure compensation amounts, and dynamically fine-tunes the currently executed collaborative control instructions based on these compensation amounts, generating corrected collaborative control instructions. The instruction distribution unit issues the corrected instructions in real time, and the actuators respond immediately, adjusting their operating parameters. By combining feedforward compensation from a digital twin model with feedback correction based on real-time estimation, the manufacturing system in Example 3 can suppress production disturbances caused by batch fluctuations in rubber compound and changes in ambient temperature, stabilizing the interfacial bond strength of mass-produced finished tires between 15.5 and 16.8 MPa, and reducing the batch-to-batch standard deviation of the rolling resistance coefficient by approximately 40%, ultimately significantly improving the consistency and stability of the performance of partitioned tread tires. Comparative Example 1 provides a partitioned tread tire produced using an existing manufacturing process without using a collaborative control system to dynamically correct the extrusion process. Performance comparison tests were conducted on 100 low-energy-consumption partitioned tread tires for new energy vehicles produced in Example 3 and 100 partitioned tread tires produced using the existing manufacturing process in Comparative Example 1. The comparative test results show that the average interfacial bond strength of the low-energy-consumption partitioned tread tires for new energy vehicles produced in Example 3 is 16.2 MPa, with a standard deviation of 0.4 MPa; while the average interfacial bond strength of the partitioned tread tires produced using the existing manufacturing process in Comparative Example 1 is 14.1 MPa, with a standard deviation of 1.5 MPa. Meanwhile, the average rolling resistance coefficient of the low-energy-consumption zoned tread tire for new energy vehicles produced in Example 3 was 0.0068, with a standard deviation of 0.0002; the average rolling resistance coefficient of the zoned tread tire produced by the existing manufacturing process in Comparative Example 1 was 0.0075, with a standard deviation of 0.0005. The experimental data objectively demonstrate that the low-energy-consumption zoned tread tire for new energy vehicles manufactured using the collaborative control system has higher interfacial bonding strength and better performance consistency.

[0039] Regarding the training process of the performance gradient and process parameter mapping model, the specific data processing path and corresponding formulas for normalizing the collected historical production data by performing maximum and minimum value processing are as follows:

[0040] In the above normalization formula, This represents the value after normalization. This indicates the specific values ​​of historical process parameter combinations or the specific values ​​of actual performance gradient data in the collected historical production data. This represents the minimum value of a combination of historical process parameters or the minimum value of measured performance gradient data in the collected historical production data. This represents the maximum value of historical process parameter combinations or the maximum value of measured performance gradient data from the collected historical production data. The collaborative control system uses an optimization algorithm to optimize the initial collaborative control commands output by the performance gradient-process parameter mapping model. The specific data processing path and corresponding formula for the objective function of the optimization algorithm are as follows:

[0041] In the above objective function formula, This represents the output value of the objective function of the optimization algorithm; The first weighting coefficient representing the preset interface bonding strength; This represents the predicted value of the interfacial bonding strength between the central region S1 compound, the shoulder region S2 compound, and the base compound S3 compound after co-extrusion, as predicted by the performance gradient and process parameter mapping relationship model. The second weighting coefficient represents the deviation of the preset rolling resistance coefficient of the finished tire; This represents the predicted value of the rolling resistance coefficient of the finished tire, obtained from the performance gradient and process parameter mapping relationship model. This indicates the target value of the rolling resistance coefficient of the finished tire as defined in the preset performance gradient instruction; This represents the absolute value of the deviation between the predicted rolling resistance coefficient of the finished tire and the target value of the rolling resistance coefficient of the finished tire as defined in the preset performance gradient instruction.

[0042] The following is an example of a data processing path that includes specific numerical values: Assume that in a piece of historical production data extracted, the specific value of the temperature data within the historical process parameter combination is... Celsius, the minimum temperature value within the historical process parameter combination in historical production data. The maximum temperature value within the historical process parameter combination in historical production data is [temperature value]. Degrees Celsius. Substitute the measured and boundary values ​​above into the normalization formula for calculation:

[0043] In the above normalization formula with specific numerical values, This represents the value after normalization. This indicates the specific numerical value of temperature data within the historical process parameter combinations in the collected historical production data; This represents the minimum temperature value among the historical process parameter combinations in the collected historical production data. This represents the maximum temperature value among the historical process parameter combinations collected from historical production data. The normalized value is calculated using the above normalization formula with specific numerical values. .

[0044] Assuming the collaborative control system uses an optimization algorithm for optimization calculations, the first weighting coefficient for the interface bonding strength is set to... The predicted values ​​of the interfacial bonding strength between the central region S1 compound, the shoulder region S2 compound, and the base compound S3 compound after co-extrusion, obtained by the performance gradient and process parameter mapping relationship model, are as follows: MPa; the second weighting coefficient for the pre-set deviation of the finished tire rolling resistance coefficient is set to... The predicted value of the rolling resistance coefficient of the finished tire, obtained from the performance gradient and process parameter mapping relationship model, is: The target value for the rolling resistance coefficient of the finished tire, as defined in the preset performance gradient instruction, is set to... Substitute the above values ​​into the objective function formula for calculation:

[0045] In the above objective function formula with specific numerical values, This represents the output value of the objective function of the optimization algorithm; The first weighting coefficient representing the preset interface bonding strength; This represents the predicted value of the interfacial bonding strength between the central region S1 compound, the shoulder region S2 compound, and the base compound S3 compound after co-extrusion, as predicted by the performance gradient and process parameter mapping relationship model. The second weighting coefficient represents the deviation of the preset rolling resistance coefficient of the finished tire; This represents the predicted value of the rolling resistance coefficient of the finished tire, obtained from the performance gradient and process parameter mapping relationship model. This represents the target value of the rolling resistance coefficient of the finished tire as defined in the preset performance gradient command. The optimization algorithm takes minimizing the output value of the objective function as the optimization calculation direction, and continuously adjusts the cooperative control command until the output value of the objective function reaches a convergent state.

[0046] The digital twin model in the collaborative control system is a fluid-solid coupling computational model constructed based on the finite volume method. A three-dimensional mesh geometric model of the digital twin is constructed based on the internal flow channel dimensions of the composite mold in the physical production line. Subsequently, the digital twin model parses the preset performance gradient commands and preliminary collaborative control commands into fluid and thermal boundary conditions at the inlet of the three-dimensional mesh geometric model, and solves the Navier-Stokes equations, including mass conservation, momentum conservation, and energy conservation equations, within the three-dimensional mesh geometric model. By solving the Navier-Stokes equations, the digital twin model calculates the velocity, pressure, and temperature field distributions of the three adhesive materials within the flow channel. Next, the digital twin model extracts the shear stress and temperature data at the interface of the adhesive materials and substitutes these data into a preset Arrhenius interfacial crosslinking kinetics empirical formula to finally calculate the predicted virtual interfacial bonding strength and virtual material property distribution.

[0047] The real-time performance estimator in the collaborative control system is constructed using a support vector regression algorithm. During the steady-state operation phase of the tire production line, 1000 sample pairs containing historical process parameter combinations and historical finished tire performance indicators are collected and used as training data for the real-time performance estimator. In the training phase, the real-time performance estimator uses a radial basis function kernel to map the input real-time process parameter data to a high-dimensional feature space and solves for the optimal feature hyperplane parameters by minimizing an objective function that includes structural and empirical risks. In the inference phase, the real-time performance estimator receives the latest real-time process parameter data and inputs it into the support vector regression computation network with the optimal feature hyperplane parameters. Finally, the support vector regression computation network estimates the real-time performance gradient of the tire segment manufactured at the current moment based on the latest input real-time process parameter data.

[0048] The performance gradient and process parameter mapping model has a preset error threshold of 0.001 during the training phase. When the loss function calculated by the parameter optimization algorithm during iteration is less than 0.001, the algorithm determines that the performance gradient and process parameter mapping model has reached convergence. The preset threshold for the interface bonding strength defined by the performance gradient command in the collaborative control system is 15 MPa. If the virtual interface bonding strength predicted by the digital twin model is lower than 15 MPa, the collaborative control system generates a process parameter feedforward compensation command to increase the set temperature of the mold area. The deviation and compensation rule base maintained internally by the collaborative control system has a hysteresis loss deviation trigger threshold of 0.005. When the absolute difference between the regional hysteresis loss value estimated by the real-time performance estimator and the target hysteresis loss value defined by the preset performance gradient command is greater than 0.005, the collaborative control system extracts a specific temperature compensation value from the deviation and compensation rule base and generates a corrected collaborative control command based on the extracted temperature compensation value.

Claims

1. A low-energy-consumption partitioned tread tire for new energy vehicles, comprising a tread having a driving surface formed by a crown rubber, the crown rubber being divided along the tire width direction into a central region S1, two shoulder regions S2 located on both sides of the central region S1, and a base rubber layer S3 laid beneath the central region S1 and the shoulder regions S2, characterized in that, The crown rubber in the central region S1, the crown rubber in the shoulder region S2, and the base rubber S3 are made of three different rubber composite materials. The tire is manufactured according to a collaborative control command output by a collaborative control system, so that the interfacial bonding strength and material property distribution between the co-extruded composite materials in the central region S1, the shoulder region S2, and the base rubber S3 reach the target relationship defined by the preset performance gradient command. The collaborative control command is obtained by the collaborative control system based on the preset performance gradient command and real-time process parameter data from the tire production line, through a performance gradient and process parameter mapping relationship model, and distributed to multiple actuators processing the rubber materials.

2. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 1, characterized in that, The performance gradient and process parameter mapping model is obtained in the following way: Collect historical production data, which includes multiple sets of historical process parameter combinations, as well as measured data on the performance gradient of the zoned rubber compound in the finished tire corresponding to each set of historical process parameter combinations. The historical production data is used to train the model, generating a performance gradient and process parameter mapping model that reflects the correspondence between the combination of process parameters and the performance gradient of the zoned rubber compound.

3. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 2, characterized in that, During the manufacturing process, the collaborative control system also compares the current performance gradient reflected by the real-time process parameter data with the preset performance gradient command to obtain the comparison result, and corrects the collaborative control command based on the comparison result.

4. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 3, characterized in that, The real-time process parameter data is collected synchronously through a sensor network deployed on the tire production line and aligned with the time sequence based on timestamps. It includes temperature data, pressure data, and flow rate data of the central region S1 rubber compound, the tire shoulder region S2 rubber compound, and the base rubber S3 rubber compound during the co-extrusion compounding process.

5. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 4, characterized in that, During the manufacturing process, the collaborative control system also uses optimization algorithms to optimize the initial collaborative control commands output by the performance gradient and process parameter mapping relationship model; The optimization algorithm aims to maximize the interface bonding strength while minimizing the deviation of the rolling resistance coefficient of the finished tire from the preset performance gradient command.

6. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 5, characterized in that, During the manufacturing process, the collaborative control system also performs feedforward adjustments based on a digital twin model; The digital twin model simulates the compounding process of the adhesive in virtual space based on the preset performance gradient command and the cooperative control command, and predicts the virtual interface bonding strength and virtual material property distribution. The collaborative control system adjusts the collaborative control commands based on the prediction results.

7. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 6, characterized in that, The comparison result is the deviation between the current performance gradient and the preset performance gradient instruction; The collaborative control system has a pre-set deviation and compensation rule library. The collaborative control system queries the deviation and compensation rule library according to the deviation value to obtain the corresponding process parameter compensation amount, and generates a corrected collaborative control command based on the process parameter compensation amount.

8. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 7, characterized in that, The preset performance gradient instruction defines that the first hysteresis loss of the tread rubber in the central region S1 at 0°C is greater than the second hysteresis loss of the tread rubber in the shoulder region S2 at 60°C.

9. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 8, characterized in that, The preset performance gradient instruction also defines that the absolute value of the difference between the 10% secant modulus of the base rubber S3 at 23°C and the modulus of the crown rubber in the central region S1 does not exceed 10%, and the absolute value of the difference between the hysteresis loss at 60°C and the hysteresis loss of the crown rubber in the shoulder region S2 does not exceed 15%.

10. The low-energy-consumption zoned tread tire for new energy vehicles according to claim 9, characterized in that, The plurality of actuators include a first rubber extrusion mechanism, a second rubber extrusion mechanism, a third rubber extrusion mechanism, a composite mold temperature control mechanism, and a pressure application mechanism; The coordinated control commands include independent flow rate and temperature commands sent to the first rubber extrusion mechanism, the second rubber extrusion mechanism, and the third rubber extrusion mechanism, respectively, as well as temperature and pressure commands sent to the composite mold temperature control mechanism and the pressure application mechanism.

Images