Digital twin system and method for tire production

Abstract

This invention relates to the field of tire manufacturing technology, and in particular to a digital twin system and method for tire production, comprising: a multimodal data acquisition layer, a holographic quality archive construction layer, an intelligent matching and decision optimization layer, a flexible sorting execution layer, and a data service and interaction platform. It completely breaks down data silos, establishing a complete and structured digital twin archive for each tire, improving management quality. Furthermore, the system no longer performs simple binary judgments, but instead seeks the optimal match between tires and orders, maximizing the satisfaction of personalized customer needs and significantly enhancing product added value and customer satisfaction. Secondly, through a multi-objective optimization algorithm, it can comprehensively consider multiple factors such as inventory, order priority, and sorting efficiency to achieve intelligent scheduling and optimal allocation of tire inventory, reducing the waste of high-quality tires and the ineffective inventory of substandard tires, thereby improving overall operational efficiency.

Description

Technical Field

[0001] This invention relates to the technical field of tire manufacturing, and in particular to a digital twin system and method for tire manufacturing. Background Technology

[0002] The final stage of tire production, namely the final inspection and sorting after vulcanization, is crucial for ensuring product quality, meeting customer needs, and realizing product value. Currently, a modern tire production line typically connects multiple high-precision testing devices, such as uniformity testing machines, dynamic balancing machines, X-ray inspection machines, and visual inspection stations, each generating massive amounts of data reflecting specific dimensions of tire quality. However, this data and the corresponding decision-making processes face significant technical challenges, becoming a bottleneck restricting production efficiency and maximizing value. Firstly, the independent operation of each testing device results in data with varying formats and scattered storage, lacking a unified data aggregation and correlation system with each individual tire as a unique index. Data such as the uniformity force spectrum, imbalance phase, internal defect images, and external blemish coordinates of a single tire are fragmented, failing to form a complete and structured description of its quality status. This leads to one-sided quality assessments, hindering comprehensive quality ratings and making it difficult to support in-depth analysis and traceability based on multi-dimensional quality. Secondly, most existing sorting systems operate based on pre-set, simple, and fixed rules. For example, simply sorting tires into qualified and unqualified categories based on whether the uniformity first-level force (RFV1H) exceeds the general standards of the supplier (such as the automotive OEM) cannot meet the needs of flexible orders. High-end customers have multi-dimensional and high-precision personalized matching requirements for tires (such as requiring the weight difference of tires on the same axle to be less than 10 grams, or the phase distribution of dynamic imbalance to be uniform); while ordinary replacement market customers may be more concerned about cost-effectiveness. Rigid sorting rules cannot allocate the right tires to the orders that need them most, resulting in a value mismatch of "selling high-quality tires at low prices" or "order requirements not being met." It also cannot achieve intelligent combination of superior tires to compensate for inferior ones. For example, two tires with slight defects in a single indicator but complementary defect characteristics (e.g., one with slightly large radial force fluctuation but excellent dynamic balance, and the other with the opposite) may be wasted if judged as "defective" on their own. In fact, using them together or matching them to models that are not sensitive to the corresponding indicators may fully meet the requirements. The current system lacks the intelligent decision-making ability to perform such multi-tire collaborative matching and compensation. Third, due to the lack of a structured "quality file" covering the entire lifecycle of a single tire, when market feedback indicates problems with a specific batch or model, quality engineers struggle to quickly and accurately pinpoint all tires in the same batch and correlate them with all process parameters and testing data from the production process for root cause analysis. Quality data cannot effectively feed back into process optimization, thus failing to form a closed-loop data system.

[0003] Therefore, there is an urgent need for a digital twin system and method for tire production to improve the above-mentioned problems. Summary of the Invention

[0004] To address the aforementioned technical challenges, this invention provides a digital twin system and method for tire production that completely breaks down data silos, establishing a complete and structured digital twin file for each tire. This improves management quality, and the system moves beyond simple binary judgments, instead seeking the optimal match between tires and orders to maximize the fulfillment of personalized customer needs, significantly enhancing product added value and customer satisfaction. Furthermore, through a multi-objective optimization algorithm, it comprehensively considers multiple factors such as inventory, order priority, and sorting efficiency, achieving intelligent scheduling and optimal allocation of tire inventory. This reduces the waste of high-quality tires and the ineffective inventory of substandard tires, improving overall operational efficiency. Finally, the structured holographic quality file enables rapid and accurate traceability of any quality issue.

[0005] The present invention provides a digital twin system for tire production, comprising: Multimodal data acquisition layer: used to acquire the unique identification code of each tire and the multi-dimensional raw quality data generated in the final inspection process; Holographic Quality Profile Construction Layer: This layer is connected to the multimodal data acquisition layer and is used to create and maintain a structured holographic quality digital twin for each tire. This twin integrates quality feature data from all dimensions associated with the tire. Intelligent Matching and Decision Optimization Layer: This layer is connected to the holographic quality profile construction layer and is used to receive and manage customer order requirements that include multi-dimensional soft and hard constraints. It also uses an optimization algorithm to perform a global optimal match between the holographic quality twin of the tire to be sorted and the order requirements, generating a tire-order allocation scheme and sorting instructions. Flexible sorting execution layer: It is connected to the intelligent matching and decision optimization layer and is used to schedule automated equipment to perform physical sorting, conveying and stacking operations of tires according to the sorting instructions; Data service and interaction platform: A human-computer interface used to provide system monitoring, file retrieval, and data analysis.

[0006] Preferably, the multimodal data acquisition layer specifically includes: Uniformity data acquisition unit: On the uniformity testing machine, the amplitude and phase of the first to multiple harmonic components of the radial force fluctuation, lateral force fluctuation and conic effect force generated when the tire rotates under standard load are recorded. The first harmonic phase defines the absolute position of the force wave peak on the tire circumference. Dynamic balancing data acquisition unit: On the dynamic balancing testing machine, it measures the static and dynamic imbalance of the tire caused by uneven mass distribution, and accurately determines the mass of the balancing counterweight required on the inner and outer correction planes and its corresponding circumferential phase angle. Internal structure data acquisition unit: It acquires structural images of the tire's internal cords and wire rings through an X-ray imaging system, or uses a laser shear speckle interferometry system to detect near-surface delamination and bubbles, thereby identifying, locating and quantifying the type, size and distribution of internal defects; Appearance geometry data acquisition unit: integrates a high-precision laser profilometer and a multi-angle machine vision system to non-contactly measure the outer diameter, cross-sectional width and other macroscopic dimensions of the tire, and simultaneously detect, classify and locate surface defects on the tire sidewall and tread. Tire weight data acquisition unit: Through a high-precision dynamic weighing system, the total mass data of each tire is quickly and accurately acquired on the production line, with an accuracy typically reaching the gram level, providing key input for subsequent weight matching.

[0007] Preferably, the holographic quality archive construction layer specifically includes: Data cleaning and alignment module: Aligns heterogeneous data from different testing devices in terms of time and space based on the tire's unique identifier; Feature extraction and structuring: used to extract standardized, quantized feature vectors from various raw data; Multidimensional quality map generation: The extracted multidimensional feature vectors are associated with tire specifications and production batch information and encapsulated into a holographic quality object that can be accessed and calculated independently.

[0008] Preferably, the intelligent matching and decision optimization layer specifically includes: Order Management Module: Used to parse and define customer order requirements, which include hard constraints for specification matching and one or more soft constraints or optimization objectives for uniform phase distribution, weight difference, dynamic balance, and defect status. Matching modeling engine: used to model the set of tire holographic quality twins and the set of order requirements as a many-to-many allocation optimization problem; Global optimization solver: Using mixed integer programming, evolutionary algorithms or tabu search algorithms, it aims to maximize the overall order satisfaction score and solve for the optimal tire allocation scheme.

[0009] Preferably, the order management module specifically includes: Hard constraints: The system reads the specification data from the holographic quality file by scanning the tire's DOT code or RFID and compares it precisely with the order requirements; Soft constraints: The system calculates the tire allocation scheme with the highest comprehensive score based on the priority weights configured for each optimization objective using an optimization algorithm; The optimization objectives include at least: optimizing the uniform force fluctuation phase distribution among tires in the same order, controlling the weight difference between tires, optimizing the phase distribution of dynamic imbalance, and evaluating the internal defect status.

[0010] Preferably, the overall order satisfaction score comprehensively calculates the degree to which the allocation scheme satisfies the soft and hard constraints of each order, the inventory turnover rate, and the sorting path efficiency.

[0011] Preferably, the flexible sorting control layer specifically includes: Programmable Logic Controller: Receives optimal sorting instructions from the intelligent matching and decision optimization layer; Sorting robotic arm: Sorting tires according to instructions; Conveying network: Transports the sorted tires to designated locations according to instructions.

[0012] Preferably, the sorting instructions received by the programmable logic controller include not only the target location, but also a sorting sequence optimized by dynamic path planning.

[0013] Preferably, the data service and interaction platform specifically includes: Holographic file query unit: By scanning the tire ID, you can instantly access its quality data and visualization maps in all dimensions; Sorting process monitoring unit: Real-time display of sorting decision logic, execution status and efficiency indicators; Analysis and Traceability Unit: Supports multi-dimensional statistical and cluster analysis of historical quality data, quickly locates tire batches with common quality characteristics, correlates production parameters, and assists in quality improvement.

[0014] A tire manufacturing method includes the following steps: S1: Real-time collection of raw quality data of off-line tires across multiple final inspection devices, and binding it with the tire's unique identification code; S2: Build and update a holographic quality digital twin for each tire, and store all quality characteristics in a structured manner; S3: Receive customer orders and analyze the multi-dimensional matching requirements and constraints for tire quality. S4: Based on the holographic quality twin set of the current tires to be sorted and the order demand set, run the global optimization matching algorithm to calculate the optimal tire-order allocation scheme; S5: Generate a specific sorting control instruction sequence based on the allocation scheme, including the target location and optimized path; S6: Drives automated equipment in the flexible sorting execution layer to complete the physical sorting and placement of tires according to instructions; S7: Update the status of the digital twin of the sorted tires, record the allocation results, and use the process data for order delivery traceability and system model optimization.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Completely break down data silos and establish a complete, structured digital twin file for each tire to improve management quality; 2. The system no longer makes simple binary judgments, but instead seeks the best match between tires and orders to maximize the satisfaction of customers' personalized needs and significantly improve product added value and customer satisfaction. 3. Through multi-objective optimization algorithms, it can comprehensively consider multiple factors such as inventory, order priority, and sorting efficiency to achieve intelligent scheduling and optimal allocation of tire inventory, reduce the waste of high-quality tires and the ineffective inventory of substandard tires, and improve overall operational efficiency. 4. Structured holographic quality archives make tracing any quality problem fast and accurate. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of the digital twin system for tire production according to the present invention; Figure 2 This is a schematic diagram of the structure of the multimodal data acquisition layer of the present invention; Figure 3 This is a schematic diagram of the structure of the holographic quality archive construction layer of the present invention; Figure 4 This is a schematic diagram of the intelligent matching and decision optimization layer of the present invention; Figure 5 This is a schematic diagram of the flexible sorting execution layer of the present invention; Figure 6 This is a schematic diagram of the data service and interaction platform of the present invention. Detailed Implementation

[0017] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0018] like Figures 1 to 6 As shown, a digital twin system for tire production according to the present invention includes: Multimodal data acquisition layer: used to acquire the unique identification code of each tire and the multi-dimensional raw quality data generated in the final inspection process; Holographic Quality Profile Construction Layer: This layer is connected to the multimodal data acquisition layer and is used to create and maintain a structured holographic quality digital twin for each tire. This twin integrates quality feature data from all dimensions associated with the tire. Intelligent Matching and Decision Optimization Layer: This layer is connected to the holographic quality profile construction layer and is used to receive and manage customer order requirements that include multi-dimensional soft and hard constraints. It also uses an optimization algorithm to perform a global optimal match between the holographic quality twin of the tire to be sorted and the order requirements, generating a tire-order allocation scheme and sorting instructions. Flexible sorting execution layer: It is connected to the intelligent matching and decision optimization layer and is used to schedule automated equipment to perform physical sorting, conveying and stacking operations of tires according to the sorting instructions; Data service and interaction platform: A human-computer interface used to provide system monitoring, file retrieval, and data analysis; The multimodal data acquisition layer specifically includes: Uniformity data acquisition unit: On the uniformity testing machine, the amplitude and phase of the first to multiple harmonic components of the radial force fluctuation, lateral force fluctuation and conic effect force generated when the tire rotates under standard load are recorded. The first harmonic phase defines the absolute position of the force wave peak on the tire circumference. Dynamic balancing data acquisition unit: On the dynamic balancing testing machine, it measures the static and dynamic imbalance of the tire caused by uneven mass distribution, and accurately determines the mass of the balancing counterweight required on the inner and outer correction planes and its corresponding circumferential phase angle. Internal structure data acquisition unit: It acquires structural images of the tire's internal cords and wire rings through an X-ray imaging system, or uses a laser shear speckle interferometry system to detect near-surface delamination and bubbles, thereby identifying, locating and quantifying the type, size and distribution of internal defects; Appearance geometry data acquisition unit: integrates a high-precision laser profilometer and a multi-angle machine vision system to non-contactly measure the outer diameter, cross-sectional width and other macroscopic dimensions of the tire, and simultaneously detect, classify and locate surface defects on the tire sidewall and tread. Tire weight data acquisition unit: Through a high-precision dynamic weighing system, the total mass data of each tire is quickly and accurately acquired on the production line, with an accuracy typically reaching the gram level, providing key input for subsequent weight matching; The holographic quality archive construction layer specifically includes: Data cleaning and alignment module: Aligns heterogeneous data from different testing devices in terms of time and space based on the tire's unique identifier; Feature extraction and structuring: used to extract standardized, quantized feature vectors from various raw data; Multidimensional quality map generation: The extracted multidimensional feature vectors are associated with tire specifications and production batch information and encapsulated into a holographic quality object that can be accessed and calculated independently; The intelligent matching and decision optimization layer specifically includes: Order Management Module: Used to parse and define customer order requirements, which include hard constraints for specification matching and one or more soft constraints or optimization objectives for uniform phase distribution, weight difference, dynamic balance, and defect status. Matching modeling engine: used to model the set of tire holographic quality twins and the set of order requirements as a many-to-many allocation optimization problem; Global optimization solver: Using mixed integer programming, evolutionary algorithms or tabu search algorithms, it aims to maximize the overall order satisfaction score and solve for the optimal tire allocation scheme; The order management module specifically includes: Hard constraints: The system reads the specification data from the holographic quality file by scanning the tire's DOT code or RFID and compares it precisely with the order requirements; Soft constraints: The system calculates the tire allocation scheme with the highest comprehensive score based on the priority weights configured for each optimization objective using an optimization algorithm; The optimization objectives include at least: optimizing the uniform force fluctuation phase distribution among tires within the same order, controlling the weight difference between tires, optimizing the phase distribution of dynamic imbalance, and evaluating the state of internal defects. The overall order satisfaction score comprehensively calculates the degree to which the allocation plan meets the soft and hard constraints of each order, inventory turnover rate, and sorting path efficiency. The flexible sorting control layer specifically includes: Programmable Logic Controller: Receives optimal sorting instructions from the intelligent matching and decision optimization layer; Sorting robotic arm: Sorting tires according to instructions; Conveyor network: Transports sorted tires to designated locations according to instructions; The programmable logic controller receives sorting instructions that include not only the target location but also a sorting sequence optimized by dynamic path planning. The data service and interaction platform specifically includes: Holographic file query unit: By scanning the tire ID, you can instantly access its quality data and visualization maps in all dimensions; Sorting process monitoring unit: Real-time display of sorting decision logic, execution status and efficiency indicators; Analysis and Traceability Unit: Supports multi-dimensional statistical and cluster analysis of historical quality data, quickly locates tire batches with common quality characteristics, correlates production parameters, and assists in quality improvement.

[0019] A tire manufacturing method includes the following steps: S1: Real-time collection of raw quality data of off-line tires across multiple final inspection devices, and binding it with the tire's unique identification code; S2: Build and update a holographic quality digital twin for each tire, and store all quality characteristics in a structured manner; S3: Receive customer orders and analyze the multi-dimensional matching requirements and constraints for tire quality. S4: Based on the holographic quality twin set of the current tires to be sorted and the order demand set, run the global optimization matching algorithm to calculate the optimal tire-order allocation scheme; S5: Generate a specific sorting control instruction sequence based on the allocation scheme, including the target location and optimized path; S6: Drives automated equipment in the flexible sorting execution layer to complete the physical sorting and placement of tires according to instructions; S7: Update the status of the digital twin of the sorted tires, record the allocation results, and use the process data for order delivery traceability and system model optimization.

[0020] Example The customer's order requires 200 sets (800 tires in total) of the same specification. The customer is extremely sensitive to NVH (noise, vibration, and harshness) and driving range, therefore imposing strict matching requirements (soft constraints): Constraint C1: The fluctuation phase of the uniform first-order radial force (RFV1H) of the four tires mounted on the same vehicle should be distributed as evenly as possible on the circumference (ideally at 90-degree intervals) to counteract vibration. Constraint C2: The weight difference of the four tires of the same vehicle shall not exceed 15 grams; Constraint C3: Prioritize tires with small dynamic balance, and the phases of imbalance of tires on the same vehicle should also be dispersed as much as possible; Constraint C4: Absolutely no internal structural defects (such as bubbles or abnormal cords) are allowed. Workflow: Step 1: Data Acquisition and File Construction: The testing equipment at the back end of the production line inspects the tires coming off the line. Tire T-20231028001 has completed inspection, and the system has collected the following data: RFID code: T-20231028001; Uniformity: RFV1H = 8.2 N, phase = 45 degrees; RFV2H = 3.1 N, phase = 120 degrees; Dynamic balance: Unbalance amount = 12g, phase of left plane = 30 degrees, phase of right plane = 210 degrees; X-ray inspection: No internal defects (feature vector is 0); Weight: 10,235 grams; Appearance: Flawless; The system's holographic quality profile building layer immediately generates a holographic quality object for the tire, storing all its features in a structured manner; Step 2, Order Parsing and Matching Preparation: The order management module of the matching and decision optimization layer parses the OEM order and transforms the above constraints C1-C4 into input conditions for the optimization problem; Step 3, Intelligent Matching and Optimization: The matching engine matches the requirements of 800 tires with the tire profiles to create a model. The optimization solver searches with the goal of "maximizing the overall score of C1-C4". After finding tires that meet the requirements, the global optimization solver will assign a virtual label to the four tires and assign them to a virtual vehicle order slot, until the optimal or suboptimal tire combination is found for all 200 vehicle slots. Step 4: Generate and issue sorting instructions: After calculation, the optimization solver outputs a list of globally optimal or near-optimal allocation schemes. The scheme clearly indicates which vehicle slot of the customer order the selected tires should be allocated to. At the same time, in order to execute efficiently, the path planning module of the flexible sorting execution layer calculates an optimal sorting path to quickly transport the selected tires to the selected vehicle slot of the customer order. Step 5, Flexible Execution and File Update: Once the selected tires are successfully placed in the designated vehicle slots, the system automatically updates their holographic quality files, adds matched orders, and marks the selected tires' inventory status as allocated. Step Six: Continuous Learning: All matching and sorting data are recorded. If the batch of tires performs well in subsequent road tests, the system can learn this matching pattern. If individual feedback occurs, the system can quickly trace the holographic files of all tires in the same batch for in-depth analysis.

[0021] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A digital twin system for tire production, characterized in that, include: Multimodal data acquisition layer: used to acquire the unique identification code of each tire and the multi-dimensional raw quality data generated in the final inspection process; Holographic Quality Profile Construction Layer: This layer is connected to the multimodal data acquisition layer and is used to create and maintain a structured holographic quality digital twin for each tire. This twin integrates quality feature data from all dimensions associated with the tire. Intelligent Matching and Decision Optimization Layer: This layer is connected to the holographic quality profile construction layer and is used to receive and manage customer order requirements that include multi-dimensional soft and hard constraints. It also uses an optimization algorithm to perform a global optimal match between the holographic quality twin of the tire to be sorted and the order requirements, generating a tire-order allocation scheme and sorting instructions. Flexible sorting execution layer: It is connected to the intelligent matching and decision optimization layer and is used to schedule automated equipment to perform physical sorting, conveying and stacking operations of tires according to the sorting instructions; Data service and interaction platform: A human-computer interface used to provide system monitoring, file retrieval, and data analysis.

2. The digital twin system for tire production as described in claim 1, characterized in that, The multimodal data acquisition layer specifically includes: Uniformity data acquisition unit: On the uniformity testing machine, the amplitude and phase of the first to multiple harmonic components of the radial force fluctuation, lateral force fluctuation and conic effect force generated when the tire rotates under standard load are recorded. The first harmonic phase defines the absolute position of the force wave peak on the tire circumference. Dynamic balancing data acquisition unit: On the dynamic balancing testing machine, it measures the static and dynamic imbalance of the tire caused by uneven mass distribution, and accurately determines the mass of the balancing counterweight required on the inner and outer correction planes and its corresponding circumferential phase angle. Internal structure data acquisition unit: It acquires structural images of the tire's internal cords and wire rings through an X-ray imaging system, or uses a laser shear speckle interferometry system to detect near-surface delamination and bubbles, thereby identifying, locating and quantifying the type, size and distribution of internal defects; Appearance geometry data acquisition unit: integrates a high-precision laser profilometer and a multi-angle machine vision system to non-contactly measure the outer diameter, cross-sectional width and other macroscopic dimensions of the tire, and simultaneously detect, classify and locate surface defects on the tire sidewall and tread. Tire weight data acquisition unit: Through a high-precision dynamic weighing system, the total mass data of each tire is quickly and accurately acquired on the production line, with an accuracy typically reaching the gram level, providing key input for subsequent weight matching.

3. The digital twin system for tire production as described in claim 1, characterized in that, The holographic quality archive construction layer specifically includes: Data cleaning and alignment module: Aligns heterogeneous data from different testing devices in terms of time and space based on the tire's unique identifier; Feature extraction and structuring: used to extract standardized, quantized feature vectors from various raw data; Multidimensional quality map generation: The extracted multidimensional feature vectors are associated with tire specifications and production batch information and encapsulated into a holographic quality object that can be accessed and calculated independently.

4. A digital twin system for tire production as described in claim 1, characterized in that, The intelligent matching and decision optimization layer specifically includes: Order Management Module: Used to parse and define customer order requirements, which include hard constraints for specification matching and one or more soft constraints or optimization objectives for uniform phase distribution, weight difference, dynamic balance, and defect status. Matching modeling engine: used to model the set of tire holographic quality twins and the set of order requirements as a many-to-many allocation optimization problem; Global optimization solver: Using mixed integer programming, evolutionary algorithms or tabu search algorithms, it aims to maximize the overall order satisfaction score and solve for the optimal tire allocation scheme.

5. A digital twin system for tire production as described in claim 4, characterized in that, The order management module specifically includes: Hard constraints: The system reads the specification data from the holographic quality file by scanning the tire's DOT code or RFID and compares it precisely with the order requirements; Soft constraints: The system calculates the tire allocation scheme with the highest comprehensive score based on the priority weights configured for each optimization objective using an optimization algorithm; The optimization objectives include at least: optimizing the uniform force fluctuation phase distribution among tires in the same order, controlling the weight difference between tires, optimizing the phase distribution of dynamic imbalance, and evaluating the internal defect status.

6. A digital twin system for tire production as described in claim 4, characterized in that, The overall order satisfaction score comprehensively calculates the degree to which the allocation plan meets the soft and hard constraints of each order, inventory turnover rate, and sorting path efficiency.

7. A digital twin system for tire production as described in claim 1, characterized in that, The flexible sorting control layer specifically includes: Programmable Logic Controller: Receives optimal sorting instructions from the intelligent matching and decision optimization layer; Sorting robotic arm: Sorting tires according to instructions; Conveying network: Transports the sorted tires to designated locations according to instructions.

8. A digital twin system for tire production as described in claim 7, characterized in that, The programmable logic controller receives sorting instructions that include not only the target location but also a sorting sequence optimized by dynamic path planning.

9. A digital twin system for tire production as described in claim 1, characterized in that, The data service and interaction platform specifically includes: Holographic file query unit: By scanning the tire ID, you can instantly access its quality data and visualization maps in all dimensions; Sorting process monitoring unit: Real-time display of sorting decision logic, execution status and efficiency indicators; Analysis and Traceability Unit: Supports multi-dimensional statistical and cluster analysis of historical quality data, quickly locates tire batches with common quality characteristics, correlates production parameters, and assists in quality improvement.

10. A tire manufacturing method, characterized in that, A method for tire production using a digital twin system for tire production according to any one of claims 1-9, comprising the following steps: S1: Real-time collection of raw quality data of off-line tires across multiple final inspection devices, and binding it with the tire's unique identification code; S2: Build and update a holographic quality digital twin for each tire, and store all quality characteristics in a structured manner; S3: Receive customer orders and analyze the multi-dimensional matching requirements and constraints for tire quality. S4: Based on the holographic quality twin set of the current tires to be sorted and the order demand set, run the global optimization matching algorithm to calculate the optimal tire-order allocation scheme; S5: Generate a specific sorting control instruction sequence based on the allocation scheme, including the target location and optimized path; S6: Drives automated equipment in the flexible sorting execution layer to complete the physical sorting and placement of tires according to instructions; S7: Update the status of the digital twin of the sorted tires, record the allocation results, and use the process data for order delivery traceability and system model optimization.

Images