Intelligent process design and verification integrated platform and method for ring forging

Abstract

The application provides an intelligent process design and verification integrated platform and method for ring forgings, applied to the field of intelligent automatic manufacturing technology. It comprises: a process management layer taking the processing mechanism model of each processing procedure in the process route of ring forging forming as the benchmark, constructing a dynamic mapping model for each processing procedure according to the equipment operation program parameters corresponding to the mechanical equipment used for each processing procedure and the numerical simulation parameters when simulating each processing procedure; a big data analysis layer adopts a station task algorithm to establish data flow correlation rules according to the virtual mirror image of the production line of the process route, then determines the current processing procedure from multiple processing procedures and inputs the actual execution data and real-time related state of the current processing procedure into the target dynamic mapping model of the current processing procedure to obtain the current equipment operation program parameters, then performs numerical simulation on the current processing procedure to generate a numerical simulation prediction result. The full-process design and verification of ring forgings in different processing procedures can be realized.

Description

Technical Field

[0001] This application relates to the field of intelligent automated manufacturing technology, and in particular to an integrated platform and method for intelligent process design and verification of ring forgings. Background Technology

[0002] In the aerospace field, ring forgings (such as ring forgings) are key load-bearing components. Their forming process involves multiple complex hot working processes such as billet preparation, ring rolling, and bulging, requiring extremely high standards for microstructure and performance control. Currently, although numerical simulation technology is widely used in process design and optimization, it still faces significant challenges in practical engineering applications, specifically manifested in three major technical bottlenecks: poor parameter matching, limitations in data acquisition, and insufficient equipment synergy.

[0003] Therefore, building an intelligent design and verification system that integrates physical mechanisms, high-frequency data, and cross-device collaboration has become an urgent need to break through current technical bottlenecks and achieve precise manufacturing of ring forgings. Summary of the Invention

[0004] This application provides an integrated platform and method for intelligent process design and verification of ring forgings. By constructing an integrated solution that integrates multiple technologies, it effectively solves three major technical bottlenecks. It can be applied to the design and verification of the entire forming process of ring forgings made of difficult-to-deform materials in the high-end manufacturing field at different processing stages, providing technical support for the high-precision and high-reliability production of high-end ring forgings.

[0005] This application also provides an integrated intelligent process design and verification platform for ring forgings, comprising: a process management layer and a big data analysis layer; wherein, The process management layer is used to obtain the process route corresponding to the ring forging, which includes multiple processing steps. For each processing step, based on the processing mechanism model of the processing step, and according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step, a dynamic mapping model corresponding to the processing step is constructed. The multiple processing steps include at least a heating step, a forging step, a rolling step, and a heat treatment step. The big data analysis layer is used to establish data flow association rules across equipment processing steps based on the virtual mirror of the production line of the process route and using a workstation task algorithm; according to the data flow association rules, the current processing step is determined from the heating step, the forging step, the rolling step, and the heat treatment step; before the current processing step is executed, the actual execution data and real-time related status of the current processing step are input into the target dynamic mapping model corresponding to the current processing step to obtain the current equipment running program parameters output by the target dynamic mapping model; and numerical simulation is performed on the current processing step based on the current equipment running program parameters to generate the numerical simulation prediction results of the ring forging in the current processing step.

[0006] According to an embodiment of this application, an integrated intelligent process design and verification platform for ring forgings is provided. The big data analysis layer is used to establish data flow association rules across equipment processing steps based on a virtual production line image of the process route and a workstation task algorithm. Specifically, the big data analysis layer is used to determine the mechanical equipment and equipment occupancy time of the ring forging in each processing step based on the process route and the hot working parameters of each processing step; based on the mechanical equipment and equipment occupancy time of each processing step, combined with the working hours of each shift, to determine the time period occupied by each processing step on the corresponding mechanical equipment; and based on all time periods, to establish data flow association rules across equipment processing steps.

[0007] According to an embodiment of this application, an integrated intelligent process design and verification platform for ring forgings is provided. The big data analysis layer is used to determine the current processing step from the heating step, the forging step, the rolling step, and the heat treatment step according to the data flow association rules. Specifically, the big data analysis layer is used to determine the processing completion trigger event of the previous processing step and the current ring forging forming parameters according to the data flow association rules; determine the target trigger conditions satisfied by the processing completion trigger event and the current ring forging forming parameters from the trigger conditions of the heating step, the forging step, the rolling step, and the heat treatment step, and take the processing step corresponding to the target trigger conditions as the current processing step.

[0008] According to an embodiment of this application, an integrated platform for intelligent process design and verification of ring forgings is provided. When the processing step is a heating step, the process management layer is used to construct a dynamic mapping model corresponding to the processing step based on the processing mechanism model of the processing step, according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step. Specifically, the process management layer is used to construct a dynamic mapping model between the temperature field, thermal stress field, and phase ratio field and the heating curve and the furnace atmosphere based on the transient nonlinear heat conduction equation, radiation and convection heat transfer boundary condition model, and solid phase change dynamics model of the heating step.

[0009] According to an embodiment of this application, an integrated platform for intelligent process design and verification of ring forgings is provided. When the processing step is a forging step, the process management layer is used to construct a dynamic mapping model corresponding to the processing step based on the processing mechanism model of the processing step, according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step. Specifically, the process management layer is used to construct a dynamic mapping model between the strain field, strain rate field, temperature field, rheological stress, and dynamic recrystallization fraction and grain size, and the press slide stroke, slide speed, forging force and number of operations, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation and damage model of the forging step.

[0010] According to an embodiment of this application, an integrated platform for intelligent process design and verification of ring forgings is provided. When the processing step is a rolling step, the process management layer is used to construct a dynamic mapping model corresponding to the processing step based on the processing mechanism model of the processing step, according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step. Specifically, the process management layer is used to construct a dynamic mapping model between the strain field, temperature field, ring size change and microstructure evolution, and the main roll speed, core roll feed speed, rolling time and guide roll position, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation, damage model and ring rolling kinematics and bite-in condition model of the rolling step.

[0011] According to an embodiment of this application, an integrated intelligent process design and verification platform for ring forgings is provided. When the processing step is a heat treatment step, the process management layer is used to construct a dynamic mapping model corresponding to the processing step based on the processing mechanism model of the processing step, according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step. Specifically, the process management layer is used to construct a dynamic mapping model between the temperature-time history, static recrystallization fraction evolution, grain size evolution, precipitate fraction and size distribution, residual stress field and final mechanical properties, and the heat treatment curve and furnace atmosphere control, based on the static recrystallization and grain growth model, precipitation kinetics model, phase transformation kinetics model and heat conduction equation of the heat treatment step.

[0012] According to an embodiment of this application, an integrated platform for intelligent process design and verification of ring forgings is provided. The sensor layer is specifically used to receive the actual manufacturing data of the ring forgings collected by sensors and a dedicated detection unit after the current processing step is completed. The sensors and the dedicated detection unit are located on the mechanical equipment used in the current processing step.

[0013] According to an embodiment of this application, an integrated platform for intelligent process design and verification of ring forgings is provided. The sensor layer is further used to integrate the equipment data of the mechanical equipment used in each processing step and the relevant process data of the ring forgings in each processing step through the industrial Ethernet protocol, so as to construct a full-process process-equipment data pool.

[0014] According to an embodiment of this application, an integrated intelligent process design and verification platform for ring forgings is provided. The actual manufacturing data includes at least the actual forming size, mechanical property test results, actual temperature curve, actual deformation force curve, and actual grain size. The numerical simulation prediction results include at least the predicted forming size, mechanical property prediction results, predicted temperature curve, predicted deformation force curve, and predicted grain size. The output results of the deviation evaluation model include at least the difference between the actual forming size and the predicted forming size, the difference between the mechanical property test results and the mechanical property prediction results, the difference between the actual temperature curve and the predicted temperature curve, the difference between the actual deformation force curve and the predicted deformation force curve, and the difference between the actual grain size and the predicted grain size.

[0015] According to an embodiment of this application, an integrated platform for intelligent process design and verification of ring forgings is provided. The quality management layer is further configured to automatically feed back the output result to the process management layer if the output result of the deviation evaluation model meets the preset conditions.

[0016] An integrated intelligent process design and verification platform for ring forgings provided according to an embodiment of this application further includes a sensor layer and a quality management layer; wherein, the sensor layer is used to collect actual manufacturing data during the forming of the ring forging after the current processing step is completed; the quality management layer is used to compare and analyze the actual manufacturing data with the numerical simulation prediction results to establish a deviation evaluation model; the process management layer is also used to update the model parameters of the target dynamic mapping model according to the output results of the deviation evaluation model.

[0017] An integrated intelligent process design and verification platform for ring forgings provided according to an embodiment of this application further includes a single-piece traceability layer. The single-piece traceability layer is used to generate an electronic identifier for the ring forging based on the work order number of the work order to which the ring forging is located and the serial number of the ring forging; receive simulated design parameters and quality inspection results of the ring forging collected by identification terminals installed at each processing step, as well as equipment operation data of the machinery used in each processing step; associate the simulated design parameters, the quality inspection results, and the equipment operation data with the electronic identifier, and construct a traceability database for the ring forging based on the association results.

[0018] This application provides an intelligent process design and verification method for ring forgings, applied to an integrated intelligent process design and verification platform for ring forgings as described above, the platform including a process management layer and a big data analysis layer; the method includes: The process route corresponding to the ring forging is obtained through the process management layer. The process route includes multiple processing steps. For each processing step, based on the processing mechanism model of the processing step, and according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step, a dynamic mapping model corresponding to the processing step is constructed. The multiple processing steps include at least a heating step, a forging step, a rolling step, and a heat treatment step. Based on the virtual mirror of the production line of the process route, the big data analysis layer establishes data flow association rules across equipment processing steps using a workstation task algorithm. According to these data flow association rules, the current processing step is determined from the heating step, forging step, rolling step, and heat treatment step. Before the current processing step is executed, the actual execution data and real-time related status of the current processing step are input into the target dynamic mapping model corresponding to the current processing step, obtaining the current equipment running program parameters output by the target dynamic mapping model. Numerical simulation is then performed on the current processing step based on the current equipment running program parameters to generate the numerical simulation prediction results of the ring forging in the current processing step.

[0019] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the intelligent process design and verification method for ring forgings as described above.

[0020] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the intelligent process design and verification method for ring forgings as described above.

[0021] The intelligent process design and verification integrated platform and method for ring forgings provided in this application embodiment, through the process management layer, is used to construct a dynamic mapping model between numerical simulation parameters and equipment operating program parameters based on the processing mechanism model of each processing step in the process route. This enables one-click conversion from numerical simulation parameters to equipment operating program parameters, thereby realizing the mapping from virtual design to real manufacturing. The big data analysis layer is used to construct a virtual image of the production line of the process route, realizing complete transparency of the production process and providing the possibility for accurate decision-making and rapid response to anomalies. Based on the virtual image of the production line, a workstation task algorithm is used to establish data flow relationships across equipment processing steps. The association rules establish a linkage adjustment mechanism between "preceding processing data and subsequent processing parameters," completely eliminating information silos and production breakpoints between equipment and minimizing waiting time between processing steps. Based on the data flow association rules, the current processing step is determined. Before the current processing step is executed, the actual execution data and real-time related status of the current processing step are input into the target dynamic mapping model corresponding to the current processing step, obtaining the current equipment running program parameters output by the target dynamic mapping model. Numerical simulation is then performed based on the current equipment running program parameters to generate numerical simulation prediction results for the ring forging in the current processing step.

[0022] The platform constructs a dynamic mapping model that integrates processing mechanism models and real-time data, accurately transforming numerical simulation parameters into equipment operating program parameters. It utilizes high-frequency acquired actual execution data for feedforward prediction, breaking down the barriers between virtual simulation and physical execution. This enables adaptive matching of process parameters and data-driven closed-loop optimization. Furthermore, based on a virtual production line mirror, it establishes cross-equipment data flow association rules using workstation task algorithms. This dynamically determines the current processing step and triggers data and instruction linkage between upstream and downstream equipment, transforming the traditional isolated equipment operation mode into a collaborative production process driven by a unified digital thread. This achieves intelligent collaboration and seamless connection of equipment throughout the entire process. The entire process, through the construction of an integrated solution that integrates multiple technologies, is applicable to the design and verification of the entire forming process of difficult-to-deform material ring forgings in high-end manufacturing, covering different processing stages. This provides technical support for the high-precision and high-reliability production of high-end ring forgings. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is one of the structural schematic diagrams of the integrated intelligent process design and verification platform for ring forgings provided in the embodiments of this application; Figure 2 This is a schematic diagram of the virtual image of the production line provided in the embodiments of this application; Figure 3a This is the second schematic diagram of the integrated intelligent process design and verification platform for ring forgings provided in this application embodiment; Figure 3b This is the third schematic diagram of the integrated intelligent process design and verification platform for ring forgings provided in this application embodiment; Figure 4 This is a schematic diagram of the program interface of the billet parameter conversion model provided in the embodiments of this application; Figure 5 This is a schematic diagram of the program interface of the ring rolling parameter conversion model provided in the embodiments of this application; Figure 6 This is a schematic diagram of a production operation plan Gantt chart provided in an embodiment of this application; Figure 7 This is a flowchart illustrating the intelligent process design and verification method for ring forgings provided in this application embodiment. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] To better understand the embodiments of this application, the three major technical bottlenecks in the prior art are first described in detail: I. Poor parameter matching: The computational logic between numerical simulation parameters and equipment executable parameters (i.e. equipment operating program parameters) is disconnected, and there is a lack of a mechanism-driven unified mapping model, that is, there is no unified mapping standard. This results in a less than 60% match between simulation predictions (i.e. numerical simulation prediction results) and actual production (i.e. actual manufacturing data), making it difficult to directly guide process setting.

[0027] II. Limitations of Data Collection: The acquisition of multi-source process data during the molding and manufacturing process is limited to the basic operating parameters of the equipment. It lacks sufficient perception of core physical field parameters such as the real-time temperature of the billet and the dynamic strain field, and cannot achieve deep coupling analysis between numerical simulation results and the manufacturing process, which restricts the accurate evaluation and feedback optimization of process effects.

[0028] III. Insufficient equipment coordination: Each processing step uses a single machine that operates independently, without a cross-equipment data interaction mechanism. Data flow is interrupted between processing steps, making it difficult to build a consistent digital link for the entire process. In other words, it is impossible to build a data flow mapping relationship for the entire process of "bill making-ring rolling-bulging". The production process is controlled in a breakpoint manner, which limits the improvement of overall process consistency and stability.

[0029] Therefore, to address the aforementioned three major technical bottlenecks, this application provides an integrated platform and method for intelligent process design and verification of ring forgings. This platform includes a process management layer and a big data analysis layer. By constructing a dynamic mapping model that integrates processing mechanism models and real-time data, numerical simulation parameters are accurately transformed into equipment operating program parameters. Furthermore, feedforward prediction is performed using high-frequency collected actual execution data, breaking down the barriers between virtual simulation and physical execution, and achieving adaptive matching of process parameters and data-driven closed-loop optimization. In addition, based on a virtual production line image, cross-equipment data flow association rules are established using workstation task algorithms. This dynamically determines the current processing step and triggers data and instruction linkage between upstream and downstream equipment, transforming the traditional isolated equipment operation mode into a collaborative production process driven by a unified digital thread. This achieves intelligent collaboration and seamless connection of equipment throughout the entire process. The entire process, through the construction of an integrated solution integrating multiple technologies, is applicable to the design and verification of the entire forming process of difficult-to-deform material ring forgings in high-end manufacturing, covering different processing stages, providing technical support for the high-precision and high-reliability production of high-end ring forgings.

[0030] The following describes the application scenarios of the integrated intelligent process design and verification platform and method for ring forgings provided in the embodiments of this application: The aforementioned integrated intelligent design and verification platform and method can be applied not only to the aerospace field, but also to high-end manufacturing fields involving complex thermoplastic molding and with extremely high requirements for product quality and consistency, such as energy equipment manufacturing (e.g., nuclear power, thermal / hydropower, wind power), transportation (e.g., rail transit, shipbuilding, automobile manufacturing), and heavy machinery and military industry (e.g., engineering machinery, military equipment).

[0031] The following section elaborates on the integrated intelligent process design and verification platform for ring forgings: Figure 1 This is a schematic diagram of the integrated intelligent process design and verification platform for ring forgings provided in this application embodiment. Figure 1 As shown, the platform includes: process management layer 101 and big data analysis layer 102.

[0032] The process management layer 101 is used to obtain the process route corresponding to the ring forging forming. The process route includes multiple processing steps. For each processing step, based on the processing mechanism model of the processing step, and according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step, a dynamic mapping model corresponding to the processing step is constructed. The big data analysis layer 102 is used to establish data flow association rules across equipment processing steps based on the virtual mirror of the production line of the process route and the workstation task algorithm. According to the data flow association rules, the current processing step is determined from the heating step, forging step, rolling step and heat treatment step. Before the current processing step is executed, the actual execution data and real-time related status of the current processing step are input into the target dynamic mapping model corresponding to the current processing step to obtain the current equipment running program parameters output by the target dynamic mapping model. The current processing step is numerically simulated based on the current equipment running program parameters to generate the numerical simulation prediction results of the ring forging in the current processing step.

[0033] Among them, a ring forging refers to a workpiece or blank that is plastically deformed in a solid state by applying external force to a metal blank, thereby obtaining the desired shape and size and improving its internal structure and mechanical properties. Optionally, the material of the ring forging may include at least difficult-to-deform materials such as high-temperature alloys, titanium alloys, ultra-high-strength steel, and magnesium alloys.

[0034] A process route refers to an ordered set of processing steps that a product flows through in sequence, defining a complete processing path from raw materials to finished product. This process route includes multiple processing steps. Optionally, these multiple processing steps may include at least heating, forging, rolling, and heat treatment processes.

[0035] Processing mechanism model refers to mathematical equations or calculation models that describe the inherent laws of physical and chemical changes that occur in materials during thermal processing.

[0036] Numerical simulation parameters refer to the physical field variables and state variables used in numerical simulation software to characterize the material state, process, and final result. Optionally, these numerical simulation parameters may include at least temperature, deformation (strain), deformation time / strain rate, rheological stress, recrystallization fraction, and grain size.

[0037] Equipment operating program parameters refer to the set of programmable control instructions that directly drive the physical equipment (i.e., the mechanical equipment used in the corresponding processing step) to perform processing actions. Optionally, the equipment operating program parameters may include at least the main roll speed of the ring mill, the slide stroke and speed of the press, the heating curve of the heating furnace, and the holding temperature and time of the heat treatment furnace.

[0038] The dynamic mapping model is a computational model based on the processing mechanism model that can convert between numerical simulation parameters and equipment operation program parameters, realizing bidirectional translation and adaptive adjustment from virtual simulation space to physical execution space.

[0039] Production line virtual mirror (e.g.) Figure 2 (As shown) refers to a real-time synchronized digital copy or digital twin / digital twin model formed by using digital twin technology to create a high-fidelity model of the physical production line, machinery, equipment, materials and processes.

[0040] The workstation task algorithm is a set of rule-based or optimization-based decision logic used to dynamically assign tasks, schedule resources, and trigger data flows based on production plans, resource status, and process constraints.

[0041] Data flow association rules are predefined, event-triggered logical conditions used to specify the content, timing, and objectives of data transfer between different processing steps or different mechanical equipment.

[0042] Actual execution data of a processing step refers to the set of data obtained through measurement and collection after a specific processing step is completed. This data describes the actual processing result of that step and can serve as input for the dynamic mapping model of subsequent processing steps. Optionally, this actual execution data may include at least geometric state data, physical field state data, microstructure state data, and process traceability data.

[0043] The real-time relevant status of a machining process refers to the initial conditions and environmental states that influence the current process decision-making, which are transmitted from the previous machining process or perceived in real time through on-site sensors before the current machining process begins. Optionally, this real-time relevant status may include at least the actual workpiece temperature, actual workpiece dimensions, ambient temperature, and mold preheating temperature after the previous machining process.

[0044] Numerical simulation prediction results refer to the preliminary extrapolation and forecast of the processing results of a specific processing step, obtained through numerical simulation calculations based on the current equipment operating program parameters and real-time relevant states, before the execution of that step. Optionally, the numerical simulation prediction results may include at least predicted forming dimensions, mechanical property prediction results, predicted temperature curves, predicted deformation force curves, and predicted grain sizes.

[0045] In this embodiment, the process management layer 101 acquires each processing step in the process route and constructs a dynamic mapping model between numerical simulation parameters and equipment operating program parameters based on the processing mechanism model of each processing step. Then, based on this dynamic mapping model, through joint calculations using the numerical simulation software results and the equipment's built-in design software, a one-click conversion from numerical simulation parameters to equipment operating program parameters can be achieved, thus realizing the mapping from virtual design to real-world manufacturing. Next, the big data analysis layer 102 is a platform-level data interaction hub that can use digital twin technology to construct a virtual image of the production line for the process route based on the digital virtual models of each processing step. This enables real-time synchronization of the operating status of the mechanical equipment and process data of each processing step in the virtual space, thereby achieving complete transparency in the production process and providing support for accurate decision-making and rapid response to anomalies. This allows for the following: Based on the virtual image of the production line, a workstation task algorithm is used to establish data flow association rules across equipment processing steps. This forms a linkage adjustment mechanism of "previous processing step data - subsequent processing step parameters," completely eliminating information silos and production breakpoints between equipment and minimizing waiting time between processing steps. Then, based on these data flow association rules, the current processing step is determined. Before executing the current processing step, the actual execution data and real-time related status of the current processing step are acquired and used as input to the target dynamic mapping model corresponding to the current processing step. This yields the current equipment running program parameters output by the target dynamic mapping model. Numerical simulation is then performed based on these parameters to generate numerical simulation prediction results for the ring forging in the current processing step.

[0046] The platform constructs a dynamic mapping model that integrates processing mechanism models and real-time data, accurately transforming numerical simulation parameters into equipment operating program parameters. It utilizes high-frequency acquired actual execution data for feedforward prediction, breaking down the barriers between virtual simulation and physical execution. This enables adaptive matching of process parameters and data-driven closed-loop optimization. Furthermore, based on a virtual production line mirror, it establishes cross-equipment data flow association rules using workstation task algorithms. This dynamically determines the current processing step and triggers data and instruction linkage between upstream and downstream equipment, transforming the traditional isolated equipment operation mode into a collaborative production process driven by a unified digital thread. This achieves intelligent collaboration and seamless connection of equipment throughout the entire process. The entire process, through the construction of an integrated solution that integrates multiple technologies, is applicable to the design and verification of the entire forming process of difficult-to-deform material ring forgings in high-end manufacturing, covering different processing stages. This provides technical support for the high-precision and high-reliability production of high-end ring forgings.

[0047] In some embodiments, combined with Figure 1 , Figure 3a This is a schematic diagram of the integrated intelligent process design and verification platform for ring forgings provided in this application embodiment. Figure 3a As shown, the platform also includes a sensor layer 103 and a quality management layer 104; wherein, Sensor layer 103 is used to collect actual manufacturing data during the ring forging process after the current processing step is completed; Quality management layer 104 is used to compare and analyze actual manufacturing data with numerical simulation prediction results and establish a deviation assessment model. The process management layer 101 is also used to update the model parameters of the target dynamic mapping model based on the output of the deviation evaluation model.

[0048] The actual manufacturing data for ring forgings refers to the total physical quantities, signals, and records directly collected or measured by sensors and dedicated detection units throughout the entire ring forging production process. These data reflect the material, equipment, process, and product quality status. Furthermore, it includes the actual execution data of the current processing step and the complete set of process data within that step. Optionally, this actual manufacturing data may include at least the actual forming dimensions, mechanical property test results, actual temperature profiles, actual deformation force profiles, and actual grain sizes.

[0049] A deviation assessment model is a mathematical model or algorithm used to quantify the difference between actual manufacturing data and numerical simulation predictions. It is used to identify process deviations, assess model confidence, and provide precise direction and magnitude for parameter optimization of dynamic mapping models.

[0050] In this embodiment, after the current processing step is completed, the sensor layer 103 collects the actual manufacturing data of the ring forging, realizing high-frequency acquisition of core process parameters and providing high data breadth and depth for process optimization and problem tracing. Subsequently, the quality management layer 104 compares and analyzes the actual manufacturing data with the numerical simulation prediction results to establish a deviation evaluation model. Finally, the process management layer 101 updates the model parameters of the target dynamic mapping model based on the output of the deviation evaluation model. The entire process can reverse-verify the virtual design results (i.e., the numerical simulation prediction results) with the actual manufacturing data in the real manufacturing process, forming a closed-loop iteration of "design-verification-optimization". The entire process, through the closed-loop architecture of "virtual design-data acquisition-real-world mapping-reverse verification", constructs an integrated solution that integrates multiple technologies. It is applicable to the entire process design and verification of ring forgings made of difficult-to-deform materials in the high-end manufacturing field at different processing steps, providing technical support for the high-precision and high-reliability production of high-end ring forgings.

[0051] It should be noted that the dynamic mapping model constructed by the process management layer 101 has improved the matching accuracy between numerical simulation parameters and equipment operating program parameters from 60% to over 95%, significantly enhancing the guiding role of numerical simulation prediction results in actual production, and increasing the one-time forming qualification rate of ring forgings to 99%.

[0052] Optionally, the model parameters of the dynamic mapping model may include at least the corrected friction coefficient and the heat loss coefficient.

[0053] In some embodiments, the output of the above-mentioned deviation evaluation model may include at least the difference between the actual molding size and the predicted molding size, the difference between the mechanical property test result and the mechanical property prediction result, the difference between the actual temperature curve and the predicted temperature curve, the difference between the actual deformation force curve and the predicted deformation force curve, and the difference between the actual grain size and the predicted grain size.

[0054] Optionally, the above-mentioned deviation assessment model may include at least the calculation of mean squared error, mean absolute error, mean absolute percentage error, and key indicators (such as indicators for scalar / numerical data, indicators for field distribution / curve data, and indicators for probability distribution / statistical data).

[0055] In other words, the output of the deviation assessment model is not limited to the difference between actual manufacturing data and numerical simulation predictions.

[0056] It should be noted that different processing steps use different mechanical equipment. Specifically, the heating step uses a heating furnace, the forging step uses a forging press / bill making equipment, the ring rolling step uses a rolling mill / ring rolling mill, and the heat treatment step uses a heat treatment furnace.

[0057] In some embodiments, combined with Figure 3a , Figure 3b This is a schematic diagram of the integrated intelligent process design and verification platform for ring forgings provided in this application embodiment. Figure 3b As shown, the platform also includes: a single-item traceability layer 105; wherein, The single-piece traceability layer 105 is used to generate an electronic identifier for the ring forging based on the work order number and serial number of the ring forging; receive the simulated design parameters and quality inspection results of the ring forging collected by the identification terminals set up at each processing step, as well as the equipment operation data of the mechanical equipment used in each processing step; associate the simulated design parameters, quality inspection results, and equipment operation data with the electronic identifier, and construct a traceability database for the ring forging based on the association results.

[0058] Among them, a work order refers to a production task instruction generated and issued by the Manufacturing Execution System (MES) for a batch or a specific product, which contains core information such as product model, quantity, process route, and planned start / completion time.

[0059] Electronic identification refers to a unique digital identity assigned to each ring forging.

[0060] The simulation design parameters of a ring forging refer to the ideal process conditions and target results set for the ring forging during the numerical simulation stage. Optionally, the simulation parameters may include at least the target heating temperature, target deformation, target strain rate, ideal grain size, and predicted forming size.

[0061] The quality inspection results of ring forgings refer to the data obtained through measurement and testing after each processing step or during final inspection, reflecting the degree to which the ring forgings conform to quality standards. Optionally, the quality inspection results may include at least ultrasonic / eddy current nondestructive testing reports, actual mechanical property (such as strength and plasticity) data, dimensional reports measured by coordinate measuring machine, metallographic photographs and analysis results, etc.

[0062] Equipment operation data of mechanical equipment refers to the actual operating instructions and status logs recorded by the equipment control system when processing a specific ring forging. Optionally, the equipment operation data may include at least the actual main roll speed curve, the actual mandrel feed speed curve, the actual slide block stroke-pressure curve, and the actual heat treatment furnace temperature curve.

[0063] The traceability database is a dedicated database that centrally stores and links all key data throughout the entire lifecycle of each ring forging, enabling forward and reverse traceability across the entire chain, from raw materials to finished products and even after-sales service. When quality issues arise, it can quickly and accurately pinpoint the problematic processing step, the cause, and other affected products; at the same time, it also provides comprehensive data support for continuous quality analysis and process improvement.

[0064] In this embodiment, the single-piece traceability layer 105 can first generate an electronic identifier for the ring forging based on the work order number and serial number of the work order to which the ring forging is located. Specifically, the electronic identifier is the work order number + 4-digit serial number, such as work order number 5F03-2025080026, and the number of the first ring forging in this work order is 5F03-20250800260001. Then, the single-piece traceability layer 105 receives the simulated design parameters and quality inspection results of the ring forging collected by the identification terminals set up in each processing step, as well as the equipment operation data of the mechanical equipment in each processing step, and automatically associates these data with the aforementioned electronic identifier to obtain the association result, thereby constructing a traceability database for the ring forging. This traceability database supports reverse querying of the entire process data through the ring forging number (i.e., the electronic identifier of the ring forging), realizing precise traceability of one piece at a time.

[0065] It should be noted that, based on the single-item traceability layer 105, the single-item traceability mechanism enables accurate collection of data throughout the entire process, reducing the traceability time for quality anomalies from 24 hours to within 10 minutes, and achieving a 100% positioning accuracy.

[0066] In some embodiments, when the processing step is a heating step, the process management layer 101 is used to construct a dynamic mapping model corresponding to the processing step based on the processing mechanism model of the processing step, according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step. This may include: the process management layer 101 is specifically used to construct a dynamic mapping model between the temperature field, thermal stress field, and phase ratio field and the heating curve and the furnace atmosphere based on the transient nonlinear heat conduction equation, radiation and convection heat transfer boundary condition model, and solid phase change dynamics model of the heating step.

[0067] It should be noted that the processing mechanism model of the heating process can include at least the transient nonlinear heat conduction equation, the radiation and convection heat transfer boundary condition model, and the solid phase change dynamics model; the numerical simulation parameters can include at least the temperature field, thermal stress field, and phase ratio field; and the equipment operation program parameters can include at least the heating curve and the furnace atmosphere.

[0068] Among them, the transient nonlinear heat conduction equation is used to describe the heat transfer within the object over time; the radiation and convection heat transfer boundary condition model is used to describe how the surface of the ring forging exchanges heat with the surrounding environment (such as the furnace and air), providing boundary constraints for the above transient nonlinear heat conduction equation; the solid phase transformation kinetic model is used to describe diffusion-type phase transformations (such as recrystallization and austenite decomposition).

[0069] Alternatively, the transient nonlinear heat conduction equation is: .

[0070] in, This indicates the density of the ring forging material; This indicates the specific heat capacity of the ring forging material; Indicates temperature. Indicates time, This represents the partial derivative of temperature with respect to time, i.e., the rate of temperature change. Represents the divergence operator; Indicates thermal conductivity; Represents the temperature gradient; This indicates the rate of internal heat source generation per unit volume.

[0071] Optionally, the convection heat transfer boundary condition model is as follows: .

[0072] in, Indicates the direction of the outward normal to the boundary surface; This represents the temperature gradient along the surface normal. This refers to the heat that flows from the interior of an object to its surface through thermal conduction. Indicates the convective heat transfer coefficient; Indicates the temperature of an object's surface; This indicates the ambient temperature of the surrounding fluid.

[0073] Optionally, the radiative heat transfer boundary condition is: .

[0074] in, Emissivity represents the surface emissivity of an object and is a dimensionless number between 0 (ideal mirror, non-radiative) and 1 (ideal blackbody, with the strongest radiation capability). This represents the Stefan-Boltzmann constant; Represents the absolute temperature of an object's surface; It indicates the absolute temperature of the surrounding environment (such as the furnace wall).

[0075] Alternatively, the solid-state phase transition dynamics model is: X(t) = 1 - exp(-at) b ).

[0076] Where X(t) represents the volume fraction of the phase change at isothermal holding time t; a represents the rate constant; and b represents the Avrami exponent.

[0077] In some embodiments, when the processing step is a forging step, the process management layer 101 is used to construct a dynamic mapping model corresponding to the processing step based on the processing mechanism model of the processing step, according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step. This may include: the process management layer 101 is specifically used to construct a dynamic mapping model between the strain field, strain rate field, temperature field, rheological stress, and dynamic recrystallization fraction and grain size, and the press slide stroke, slide speed, forging force and number of operations, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation and damage model of the forging step.

[0078] It should be noted that the processing mechanism model of the forging process can include at least the plastic constitutive model, dynamic recrystallization model, heat conduction equation and damage model; the numerical simulation parameters can include at least the strain field, strain rate field, temperature field, rheological stress, and dynamic recrystallization fraction and grain size; the equipment operation program parameters can include at least the press slide stroke, slide speed, forging force and number of operations.

[0079] Among them, the plastic constitutive model is used to describe how the flow stress of the ring forging material changes with deformation conditions during plastic deformation at high temperature, and is the basis for calculating deformation force and power; the dynamic recrystallization model is used to describe how new undeformed grains nucleate and grow during the hot deformation of the ring forging material, thereby refining the grains and optimizing the microstructure; the heat conduction equation is used to describe the evolution of the internal temperature field of the workpiece with time and space; and the damage model is used to predict the generation and evolution of internal micropores and microcracks in the material during deformation, thereby assessing the risk of cracking.

[0080] Alternatively, the plastic constitutive model is: σ=(1 / α)ln{(Z / A)^(1 / n x )+[(Z / A)^(2 / n x )+1] 1 / 2}

[0081] Where σ represents rheological stress; α represents the stress level parameter; Z represents the Zener-Hollomon parameter; A represents the structural factor; n xThis indicates the stress index.

[0082] Optionally, the dynamic recrystallization model may include a kinetic model and a grain size model, wherein the kinetic model is: X drx =1-exp(-k d ((ε-ε c ) / ε 0.5 )^n d (for ε>ε) c The grain size model is: d drx =k z Z -mz .

[0083] Among them, X drx The volume fraction of dynamic recrystallization is expressed in the range of 0-1; ε represents a dimensionless quantity; ε c ε represents the critical strain, the minimum strain required for dynamic recrystallization to begin; 0.5 This represents the strain corresponding to a recrystallization fraction of 50%; d drx Indicates the average grain size after dynamic recrystallization; k d n d k z and m z These represent different material-related kinetic constants; Z represents the Zener-Horomon parameter, and mz represents the material-related experimental constant.

[0084] Alternatively, the heat conduction equation is: .

[0085] Where L represents the internal heat source term.

[0086] Alternatively, the damage model is: C=∫(σ / ¯σ)d¯ε.

[0087] Where C represents the cumulative damage value; σ ∫ represents the maximum principal stress; ¯σ represents the equivalent stress (or flow stress); ¯ε represents the equivalent strain (or deformation); ∫ represents the integral sign.

[0088] For example, the dynamic mapping model constructed by the process management layer 101 based on the processing mechanism model of the forging process is a ring rolling parameter conversion model, and the program interface of the ring rolling parameter conversion model is as follows: Figure 4 As shown. From Figure 4 As can be seen, the ring rolling parameter conversion model between the numerical simulation parameters (i.e., deformation process parameters) and the equipment operation program parameters (i.e., equipment operation parameters) of this ring rolling process can store the corresponding program number for easy subsequent calling and execution.

[0089] In some embodiments, when the processing step is a rolling step, the process management layer 101 is used to construct a dynamic mapping model corresponding to the processing step based on the processing mechanism model of the processing step, according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step. This may include: the process management layer 101 is specifically used to construct a dynamic mapping model between the strain field, temperature field, ring size change and microstructure evolution, and the main roll speed, core roll feed speed, rolling time and guide roll position, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation, damage model and ring rolling kinematics and bite-in condition model of the rolling step.

[0090] It should be noted that the processing mechanism model of the rolling process can include at least the plastic constitutive model, dynamic recrystallization model, heat conduction equation, damage model, and ring rolling kinematics and bite-in condition model; the numerical simulation parameters can include at least the strain field, temperature field, ring size change and microstructure evolution; the equipment operation program parameters can include at least the main roll speed, core roll feed speed, rolling time and guide roll position.

[0091] Among them, the ring rolling kinematic model is used to describe the geometric and velocity relationships between components such as the ring, main roll, and core roll, and establishes a quantitative relationship between equipment parameters and ring deformation parameters (such as radius growth and strain rate); the bite condition model is used to determine whether the ring rolling process can start smoothly and stably and continue. If the bite condition is not met, slippage will occur between the ring and the roll, leading to process failure.

[0092] Alternatively, the kinematic model for ring rolling is: V = π(R o 2 -R i 2 )H.

[0093] Where V represents the volume of the ring, which remains constant during deformation; R o R represents the instantaneous outer radius of the ring component. i H represents the instantaneous inner radius of the ring; H represents the height of the ring (axial dimension). Alternatively, the bite condition model is: ˙ε≈(V f ω r R r ) / (R o 2 -R i 2 ).

[0094] Where ˙ε represents the average strain rate of the ring within the rolling zone; V fω represents the radial feed speed of the core roller. r R represents the angular velocity of the main roller, which controls the rotational speed of the ring component. r This indicates the radius of the main roller.

[0095] For example, the dynamic mapping model constructed by the process management layer 101 based on the processing mechanism model of the rolling process is a billet parameter conversion model, and the program interface of the billet parameter conversion model is as follows: Figure 5 As shown. From Figure 5 As can be seen, the billet parameter conversion model between the numerical simulation parameters (i.e. deformation process parameters) and the equipment operation program parameters (i.e. equipment operation parameters) of this forging process can store the corresponding program number for easy subsequent calling and execution.

[0096] In some embodiments, when the processing step is a heat treatment step, the process management layer 101 is used to construct a dynamic mapping model corresponding to the processing step based on the processing mechanism model of the processing step, according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step. This may include: the process management layer 101 is specifically used to construct a dynamic mapping model between the temperature-time history, static recrystallization fraction evolution, grain size evolution, precipitate fraction and size distribution, residual stress field and final mechanical properties, and the heat treatment curve and furnace atmosphere control, based on the static recrystallization and grain growth model, precipitation kinetics model, phase transformation kinetics model and heat conduction equation of the heat treatment step.

[0097] It should be noted that the processing mechanism model of the forging process can include at least the static recrystallization and grain growth model, precipitation kinetics model, phase transformation kinetics model and heat conduction equation; the numerical simulation parameters can include at least the temperature-time history, static recrystallization fraction evolution, grain size evolution, precipitate fraction and size distribution, residual stress field and final mechanical properties; the equipment operation program parameters can include at least the heat treatment curve and furnace atmosphere control.

[0098] Among them, the static recrystallization and grain growth model is used to describe how, after cold or hot deformation, the twisted and broken grains of the material are replaced by new, strain-free equiaxed grains (recrystallization) during subsequent heating or holding, and how these new grains subsequently coarsen (growth); the precipitation kinetics model is used to describe the nucleation, growth, and coarsening of second-phase particles precipitated over time from a supersaturated solid solution (after solution treatment and rapid cooling); the phase transformation kinetics model is used to describe the rate and amount of transformation of a material from one crystal structure (phase) to another during heating or cooling.

[0099] Optionally, the static recrystallization model is: X srx=1-exp[-k s (t / t 0.5 )^n s ].

[0100] Among them, X srx The volume fraction of static recrystallization is between 0 and 1; t represents the holding time; t 0.5 This indicates the time required for the recrystallization volume fraction to reach 50%; k s and n s These represent the kinetic constants related to recrystallization nucleation and growth mechanisms, respectively, obtained by fitting experimental data.

[0101] Alternatively, the grain growth model is: D n’ -D0 n’ =K g t exp(-Q g / (RT)).

[0102] Where D represents the average grain size at time t; D0 represents the initial grain size after recrystallization; n' represents the grain growth index, which is related to the material and the mechanism of grain boundary migration, and usually takes a value between 2 and 4; K g Q represents the dynamic constant; g The value represents the activation energy for grain growth, reflecting the ease or difficulty of grain boundary migration; T represents the absolute temperature; and R represents the molar gas constant.

[0103] Optionally, the precipitation kinetic model is: X p =1-exp[-k p (t'-υ) b ].

[0104] Among them, X p t' represents the volume fraction of the precipitated phase; t' represents the aging time; υ ​​represents the precipitation incubation period. During this period, precipitation has not yet occurred significantly; k p denoted by , the precipitation rate constant is strongly dependent on temperature; b represents the Avrami exponent, which is related to the nucleation and growth mode of the precipitated phase.

[0105] Alternatively, the phase transition dynamics model is: ∑[Δt] i / τ i [(T)]=1.

[0106] Where ∑ represents the summation symbol, signifying the cumulative calculation over the entire cooling process; t i This indicates that at a specific temperature T iThe residence time increment under τ discretizes the continuous cooling curve into many small isothermal steps; i (T) indicates that at temperature T i The isothermal time required for the phase transformation to reach a specific transformation amount (such as 1% or 99%) is given by the material’s TTT curve or CCT curve.

[0107] In some embodiments, the big data analysis layer 102 is used to establish data flow association rules across equipment processing steps based on the virtual image of the production line of the process route and using a workstation task algorithm. This may include: the big data analysis layer 102 is specifically used to determine the mechanical equipment and equipment occupancy time used in each processing step of the ring forging based on the virtual image of the production line, the process route, and the hot processing parameters of each processing step; based on the mechanical equipment and equipment occupancy time of each processing step, combined with the working hours of each shift, determine the time period occupied by each processing step on the corresponding mechanical equipment; and establish data flow association rules across equipment processing steps based on all time periods.

[0108] Among them, hot working parameters refer to the key process condition variables used to control and describe the microstructure evolution and final mechanical properties of the ring forging material during the thermoplastic forming process. Optionally, these hot working parameters may include at least temperature parameters, deformation amount parameters, deformation rate parameters, deformation force parameters, and time parameters.

[0109] In this embodiment, the big data analysis layer 102, in establishing data flow association rules across equipment processing steps based on the virtual mirror of the production line and using a workstation task algorithm, first allocates resources and time. Specifically, it acquires the process route and the hot processing parameters of each processing step on the process route. Then, based on the process route and all hot processing parameters, it determines the mechanical equipment used in each processing step of the ring forging and the equipment occupancy time, clarifying which mechanical equipment performs each processing step and how long it needs to be performed. Next, it formulates a schedule. Specifically, it first determines resource availability constraints, i.e., the start time of each shift, and then, combined with the mechanical equipment used in each processing step and the equipment occupancy time, determines the time period occupied by each processing step on the corresponding mechanical equipment, mainly considering the sequence of processing steps. It accurately fills each processing step into the time axis of the corresponding mechanical equipment, thereby generating a production operation plan Gantt chart (e.g., ...). Figure 6As shown in the diagram, this production schedule Gantt chart is a production timetable accurate to the minute. Further, based on the logic and temporal relationships within this timetable, triggering conditions for data flow are defined to establish data flow association rules across equipment processing steps. The entire process transforms the traditional, discontinuous production model, reliant on manual scheduling and information transmission, into a data-driven, automatically collaborative, continuous flow intelligent production model. Its core value lies in transforming the production plan from a static table into a "living" system capable of dynamically directing the physical world, representing a crucial link between planning and execution.

[0110] Optionally, the triggering conditions for data flow are defined as follows: IF [The billet preparation process is scheduled to end at 08:30] THEN [The forging program will be automatically sent to the forging press at 08:25]; IF [The ring rolling process is scheduled to begin at 09:15] AND [The billet preparation process is actually completed] THEN [An automated guided vehicle (AGV) is automatically called to transport the billet to the ring rolling mill]; IF [Heat treatment process is scheduled to start at 10:00] THEN [At 09:55, the actual final rolling temperature of the ring rolling process will be used as a parameter to automatically set the process curve of the heat treatment furnace].

[0111] In some embodiments, the big data analysis layer 102 is used to determine the current processing step from the heating step, forging step, rolling step, and heat treatment step according to data flow association rules. This may include: the big data analysis layer 102 is specifically used to determine the processing completion trigger event of the previous processing step and the current ring forging forming parameters according to data flow association rules; determine the processing completion trigger event and the target trigger condition satisfied by the current ring forging forming parameters from the trigger conditions of the heating step, forging step, rolling step, and heat treatment step respectively, and take the processing step corresponding to the target trigger condition as the current processing step.

[0112] Among them, the processing completion trigger event is used to indicate that the corresponding processing step has been substantially completed.

[0113] The current forming parameters of ring forgings refer to the key physical quantities that are collected in real time during the processing of the ring forgings in the corresponding processing steps, and are used to characterize the state of the ring forgings themselves.

[0114] Triggering conditions refer to logical judgment conditions composed of the processing completion trigger event and the rules that the current ring forging forming parameters must meet.

[0115] In this embodiment, the core of the big data analysis layer 102 in determining the current processing step according to data flow association rules is to achieve real-time perception and automatic transition of the production status. Specifically, the big data analysis layer 102 continuously runs as an event-driven state machine, capable of real-time monitoring of processing completion trigger events uploaded from all mechanical equipment and online sensing systems in the virtual image of the production line. Once such an event is captured, the big data analysis layer 102 immediately initiates a multi-source data fusion and condition judgment process: First, according to the data flow association rules, it retrieves the current ring forging forming parameters bound to the processing completion trigger event, which are key quantitative indicators characterizing the immediate quality status of the ring forging billet after processing in the previous processing step. Subsequently, the big data analysis layer 102 executes the trigger condition matching logic: combining the above-mentioned processing completion trigger event with the current ring forging forming parameters into a logical criterion, and comparing it one by one with the trigger condition rule library predefined for the four core processes of heating, forging, rolling, and heat treatment. Finally, through target trigger condition identification, the big data analysis layer 102 can uniquely determine which subsequent processing step's initiation condition is fully met, thus formally establishing that processing step, i.e., the processing step corresponding to the target trigger condition, as the current processing step for the ring forging. The entire platform transforms the traditional passive response mode, which relies on manual on-site confirmation, paper document transmission, or discrete system queries, into an active driving mode triggered in real time by events and data. This enables the integrated platform to possess accurate, zero-latency process-level status tracking capabilities, ensuring millisecond-level synchronization between the digital twin virtual image and the physical production line in terms of execution rhythm. This is a key technological link in achieving seamless connection and closed-loop control from global production planning to unit-level work instructions.

[0116] For example, the completion trigger event of the heating process is the ring forging billet exiting the heating furnace, and the current ring forging forming parameter is the exit temperature; the trigger condition for the forging process is: the ring forging billet exiting the heating furnace event occurs, and the exit temperature reaches a preset temperature threshold. The forging process is triggered when the upper crossbeam of the forging press returns to its original position, and the current forming parameter of the ring forging is the post-forging height; the rolling process is triggered when the upper crossbeam of the press returns to its original position, and the post-forging height dimension is within the tolerance range. The rolling process is triggered when the ring mill spindle stops and the mandrel retracts, and the current ring forging parameters are the ring outer diameter and the final rolling temperature. The heat treatment process is triggered when the ring mill spindle stops and the mandrel retracts, and the ring outer diameter reaches the target value and the final rolling temperature is within the preset temperature range. The completion of the forging process is triggered by the opening of the heat treatment furnace door and the discharge of material. The current forming parameters of the ring forging are the actual heat treatment curve. The triggering conditions for the ring forging are: the opening of the heat treatment furnace door and the discharge of material occurs, and the matching degree between the actual heat treatment curve and the process requirement curve is greater than the preset matching degree threshold.

[0117] In some embodiments, the sensor layer 103 is specifically used to receive the actual manufacturing data of the ring forging collected by the sensor and the dedicated detection unit after the current processing step is completed. The sensor and the dedicated detection unit are located on the mechanical equipment used in the current processing step.

[0118] A sensor is a primary detection element or device that is directly installed on or around mechanical equipment to sense, measure, and convert physical states (such as displacement, temperature, and force) into standardized electrical signals. Optionally, the sensor may include at least displacement sensors, pressure sensors, temperature sensors, and other state sensors (such as vibration sensors and flow sensors).

[0119] A dedicated testing unit refers to an advanced testing system that integrates various sensors, optical devices, computing cores, and software systems to perform specific and complex measurement, identification, or analysis tasks. Optionally, this dedicated testing unit may include at least a three-dimensional geometric scanning unit (such as an infrared thermometer, a laser full-range scanner, or a machine vision system), an online non-destructive testing unit (such as an ultrasonic automatic testing system or an eddy current testing system), and an online tissue performance analysis unit (such as an online thermal imager system or a line-side rapid metallographic system).

[0120] In this embodiment of the application, after the current processing step is completed, the sensor layer 103 performs high-frequency acquisition of the actual manufacturing data of the ring forging collected by the sensor and the dedicated detection unit through the edge computing unit. The edge computing unit can sample the received actual manufacturing data according to a preset sampling frequency, such as the sampling frequency of billet temperature is 1Hz and the sampling frequency of equipment process parameters is 0.02~5Hz, in order to prepare for subsequent data comparison and analysis.

[0121] It should be noted that the sensors and dedicated detection units installed on different mechanical equipment can be the same or different; no specific limitations are made here.

[0122] In some embodiments, the sensor layer 103 is also used to integrate the equipment data of the mechanical equipment used in each processing step and the relevant process data of the ring forging in each processing step through the industrial Ethernet protocol, so as to build a full-process process-equipment data pool.

[0123] The Industrial Ethernet protocol is a real-time communication protocol standard based on Ethernet technology, applied in the field of industrial automation control. Optionally, the Industrial Ethernet protocol may include at least Process Field Network (PROFINET), Ethernet for Control Automation Technology (EtherCAT), etc.

[0124] In this embodiment, the sensor layer 103 can break down information silos by unifying the access of different manufacturers and types of mechanical equipment and control units (Programmable Logic Controller (PLC), Computer Numerical Control (CNC) systems, and sensor gateways) to the same high-speed network. This lays the physical foundation for building a full-process process-equipment data pool. In addition, compared with traditional commercial Ethernet, the use of industrial Ethernet protocol effectively ensures that key process data (such as the actual execution data and real-time related status of each processing step, actual manufacturing data, etc.) can be stably transmitted within a precise time window, meeting the stringent requirements of closed-loop control.

[0125] It should be noted that sensor layer 103 collects and covers the core parameters of the entire process, improving the equipment coordination rate to 100%, transforming the production process from breakpoint control to full-process visual control, and shortening the abnormal response time to within 5 minutes.

[0126] In some embodiments, the quality management layer 104 is further configured to automatically feed back the output results to the process management layer 101 if the output results of the deviation assessment model meet preset conditions.

[0127] In this embodiment, after determining the output of the deviation evaluation model, the quality management layer 104 can compare the output with preset conditions. If the output does not meet the preset conditions, no operation is required. If the output meets the preset conditions (e.g., greater than a preset deviation threshold of 0.5), the output is automatically fed back to the process management layer 101, enabling the process management layer 101 to update the model parameters of the target dynamic mapping model based on the output, forming a closed-loop iteration of "design-verification-optimization". The entire process automatically triggers model parameter updates through preset conditions, realizing unmanned intelligent decision-making from problem identification to process optimization, significantly improving the adaptability and accuracy of process design.

[0128] It should be noted that the quality management system 104 reduces the number of simulation trials through closed-loop optimization, thereby increasing the utilization rate of difficult-to-deform materials by at least 8%, shortening the debugging time of mechanical equipment by more than 30%, and effectively reducing production costs.

[0129] The intelligent process design and verification method for ring forgings provided in the embodiments of this application is described below. The intelligent process design and verification method for ring forgings described below can be referred to in correspondence with the integrated intelligent process design and verification platform for ring forgings described above.

[0130] Figure 7 This is a flowchart illustrating the intelligent process design and verification method for ring forgings provided in this application. Figure 7 As shown, this method is applied to, for example Figure 1 Alternatively, the intelligent process design and verification integrated platform for ring forgings shown in Figure 3 includes a process management layer and a big data analysis layer. The method includes the following steps 701-702.

[0131] Step 701: Obtain the process route corresponding to the ring forging through the process management layer. The process route includes multiple processing steps. For each processing step, based on the processing mechanism model of the processing step, construct a dynamic mapping model corresponding to the processing step according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step and the numerical simulation parameters when simulating the processing step. Among them, the multiple processing steps include at least a heating step, a forging step, a rolling step and a heat treatment step.

[0132] Optionally, the process management layer, based on the processing mechanism model of the processing step, constructs a dynamic mapping model corresponding to the processing step according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step and the numerical simulation parameters when simulating the processing step. This includes at least one of the following implementation methods: Implementation Method 1: When the processing step is a heating step, the process management layer constructs a dynamic mapping model between the temperature field, thermal stress field, phase ratio field, heating curve, and furnace atmosphere, based on the transient nonlinear heat conduction equation, radiation and convection heat transfer boundary condition model, and solid phase change dynamics model of the heating step.

[0133] Implementation Method 2: When the processing step is a forging step, the process management layer constructs a dynamic mapping model between the strain field, strain rate field, temperature field, rheological stress, dynamic recrystallization fraction and grain size, and the press slide stroke, slide speed, forging force and number of operations, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation and damage model of the forging step.

[0134] Implementation Method 3: When the processing step is rolling, the process management layer constructs a dynamic mapping model between the strain field, temperature field, ring size change and microstructure evolution, and the main roll speed, core roll feed speed, rolling time and guide roll position, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation, damage model and ring rolling kinematics and bite condition model of the rolling step.

[0135] Implementation Method 4: When the processing step is a heat treatment step, the process management layer constructs a dynamic mapping model between the temperature-time history, static recrystallization fraction evolution, grain size evolution, precipitate fraction and size distribution, residual stress field and final mechanical properties, and the heat treatment curve and furnace atmosphere control, based on the static recrystallization and grain growth model, precipitation kinetics model, phase transformation kinetics model and heat conduction equation of the heat treatment step.

[0136] Step 702: Based on the virtual mirror of the production line of the process route, the big data analysis layer establishes data flow association rules across equipment processing steps using the workstation task algorithm; based on the data flow association rules, the current processing step is determined from the heating step, forging step, rolling step, and heat treatment step; before the current processing step is executed, the actual execution data and real-time related status of the current processing step are input into the target dynamic mapping model corresponding to the current processing step to obtain the current equipment running program parameters output by the target dynamic mapping model; based on the current equipment running program parameters, numerical simulation is performed on the current processing step to generate the numerical simulation prediction results of the ring forging in the current processing step.

[0137] Optionally, the numerical simulation prediction results include at least the predicted molding size, the predicted mechanical properties, the predicted temperature profile, the predicted deformation force profile, and the predicted grain size.

[0138] Optionally, based on the virtual image of the production line in the process route, the big data analysis layer uses a workstation task algorithm to establish data flow association rules across equipment processing steps. This includes: determining the mechanical equipment and equipment occupancy time of the ring forging in each processing step based on the virtual image of the production line, the process route, and the hot processing parameters of each processing step; determining the time period occupied by each processing step on the corresponding mechanical equipment based on the mechanical equipment and equipment occupancy time of each processing step, combined with the working hours of each shift; and establishing data flow association rules across equipment processing steps based on all time periods.

[0139] Optionally, the big data analysis layer determines the current processing step from the heating, forging, rolling, and heat treatment processes based on data flow association rules. This includes: determining the processing completion trigger event of the previous processing step and the current ring forging forming parameters based on data flow association rules; determining the processing completion trigger event and the target trigger conditions satisfied by the current ring forging forming parameters from the trigger conditions of the heating, forging, rolling, and heat treatment processes, and taking the processing step corresponding to the target trigger conditions as the current processing step.

[0140] Optionally, the platform may also include a sensor layer and a quality management layer. After step 702, the method may further include: collecting actual manufacturing data of the ring forging through the sensor layer after the current processing step is completed; comparing and analyzing the actual manufacturing data with the numerical simulation prediction results through the quality management layer to establish a deviation evaluation model; and updating the model parameters of the target dynamic mapping model through the process management layer based on the output results of the deviation evaluation model.

[0141] Optionally, the actual manufacturing data shall include at least the actual molding dimensions, mechanical property test results, actual temperature profile, actual deformation force profile, and actual grain size.

[0142] Optionally, after the current processing step is completed, the actual manufacturing data of the ring forging is collected through the sensor layer, including: after the current processing step is completed, the actual manufacturing data of the ring forging collected by the sensor and the dedicated detection unit are received through the sensor layer, wherein the sensor and the dedicated detection unit are located on the mechanical equipment used in the current processing step.

[0143] Optionally, after step 703, the method further includes: integrating the equipment data of the mechanical equipment used in each processing step and the relevant process data of the ring forging in each processing step through the sensor layer via the industrial Ethernet protocol, and constructing a full-process process-equipment data pool.

[0144] Optionally, after step 704, the method further includes: if the output result of the deviation assessment model meets the preset conditions, the quality management layer automatically feeds back the output result to the process management layer.

[0145] Optionally, the output of the deviation evaluation model includes at least the difference between the actual molding size and the predicted molding size, the difference between the mechanical property test results and the mechanical property prediction results, the difference between the actual temperature curve and the predicted temperature curve, the difference between the actual deformation force curve and the predicted deformation force curve, and the difference between the actual grain size and the predicted grain size.

[0146] Optionally, the platform also includes a single-piece traceability layer. After step 702, the method further includes: generating an electronic identifier for the ring forging based on the work order number of the work order to which the ring forging is located and the serial number of the ring forging through the single-piece traceability layer; receiving the simulated design parameters and quality inspection results of the ring forging collected by the identification terminals set up at each processing step, as well as the equipment operation data of the mechanical equipment used in each processing step; associating the simulated design parameters, quality inspection results, and equipment operation data with the electronic identifier, and constructing a traceability database for the ring forging based on the association results.

[0147] In this embodiment, the technical solution described in steps 701-705 above constructs a dynamic mapping model that integrates the processing mechanism model and real-time data. This model accurately transforms numerical simulation parameters into equipment operation program parameters and utilizes high-frequency acquired actual execution data for feedforward prediction. This breaks down the barriers between virtual simulation and physical execution, achieving adaptive matching of process parameters and data-driven closed-loop optimization. Furthermore, based on a virtual production line image, a cross-equipment data flow association rule is established using a workstation task algorithm. This dynamically determines the current processing step and triggers data and instruction linkage between upstream and downstream equipment, transforming the traditional isolated equipment operation mode into a collaborative production process driven by a unified digital thread. This achieves intelligent collaboration and seamless connection of equipment throughout the entire process. The entire process, through the construction of an integrated solution that integrates multiple technologies, is applicable to the design and verification of the entire forming process of difficult-to-deform material ring forgings in the high-end manufacturing field at different processing stages, providing technical support for the high-precision and high-reliability production of high-end ring forgings.

[0148] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the intelligent process design and verification method for ring forgings provided by the above methods.

[0149] In another aspect, embodiments of this application also provide a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the intelligent process design and verification method for ring forgings provided by the methods described above.

[0150] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0151] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An integrated platform for intelligent process design and verification of ring forgings, characterized in that, include: The process management layer and the big data analysis layer; among them, The process management layer is used to obtain the process route corresponding to the ring forging, which includes multiple processing steps. For each processing step, based on the processing mechanism model of the processing step, and according to the equipment operation program parameters corresponding to the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step, a dynamic mapping model corresponding to the processing step is constructed. The multiple processing steps include at least a heating step, a forging step, a rolling step, and a heat treatment step. When the processing step is a heating step, the process management layer is specifically used to construct a dynamic mapping model between the temperature field, thermal stress field, and phase ratio field and the heating curve and the furnace atmosphere, based on the transient nonlinear heat conduction equation, radiation and convection heat transfer boundary condition model, and solid phase change dynamics model of the heating step. When the processing step is a forging step, the process management layer is specifically used to construct a dynamic mapping model between the strain field, strain rate field, temperature field, rheological stress, and dynamic recrystallization fraction and grain size, and the press slide stroke, slide speed, forging force and number of operations, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation and damage model of the forging step. When the processing step is a rolling step, the process management layer is specifically used to construct a dynamic mapping model between the strain field, temperature field, ring size change and microstructure evolution, and the main roll speed, core roll feed speed, rolling time and guide roll position, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation, damage model and ring rolling kinematics and bite condition model of the rolling step. When the processing step is a heat treatment step, the process management layer is specifically used to construct a dynamic mapping model between the temperature-time history, static recrystallization fraction evolution, grain size evolution, precipitate fraction and size distribution, residual stress field and final mechanical properties, and the heat treatment curve and furnace atmosphere control, based on the static recrystallization and grain growth model, precipitation kinetics model, phase transformation kinetics model and heat conduction equation of the heat treatment step. The big data analysis layer is used to establish data flow association rules across equipment processing steps based on the virtual mirror of the production line of the process route and using a workstation task algorithm; according to the data flow association rules, the current processing step is determined from the heating step, the forging step, the rolling step, and the heat treatment step; before the current processing step is executed, the actual execution data and real-time related status of the current processing step are input into the target dynamic mapping model corresponding to the current processing step to obtain the current equipment running program parameters output by the target dynamic mapping model; and numerical simulation is performed on the current processing step based on the current equipment running program parameters to generate the numerical simulation prediction results of the ring forging in the current processing step.

2. The integrated intelligent process design and verification platform for ring forgings according to claim 1, characterized in that, The big data analysis layer is used to establish data flow association rules across equipment processing steps based on the virtual image of the production line of the process route and using a workstation task algorithm, including: The big data analysis layer is specifically used to determine the mechanical equipment and equipment usage time of the ring forging in each processing step based on the virtual image of the production line, the process route, and the hot processing parameters of each processing step; to determine the time period occupied by each processing step on the corresponding mechanical equipment based on the mechanical equipment and equipment usage time of each processing step, combined with the working hours of each shift; and to establish data flow association rules for the cross-equipment processing steps based on all time periods.

3. The integrated intelligent process design and verification platform for ring forgings according to claim 1 or 2, characterized in that, The big data analysis layer is used to determine the current processing step from the heating step, the forging step, the rolling step, and the heat treatment step according to the data flow association rules, including: The big data analysis layer is specifically used to determine the processing completion trigger event of the previous processing step and the current ring forging forming parameters according to the data flow association rules; determine the target trigger conditions that the processing completion trigger event and the current ring forging forming parameters satisfy from the trigger conditions of the heating process, the forging process, the rolling process and the heat treatment process, and take the processing step corresponding to the target trigger conditions as the current processing step.

4. The integrated intelligent process design and verification platform for ring forgings according to claim 1 or 2, characterized in that, It also includes a sensor layer and a quality management layer; among which, The sensor layer is used to collect the actual manufacturing data of the ring forging after the current processing step is completed; The quality management layer is used to compare and analyze the actual manufacturing data with the numerical simulation prediction results to establish a deviation evaluation model. The process management layer is also used to update the model parameters of the target dynamic mapping model based on the output results of the deviation evaluation model.

5. The integrated platform for intelligent process design and verification of ring forgings according to claim 1 or 2, characterized in that, It also includes a single-item traceability layer; among which, The single-piece traceability layer is used to generate an electronic identifier for the ring forging based on the work order number of the work order to which the ring forging belongs and the serial number of the ring forging; receive the simulated design parameters and quality inspection results of the ring forging collected by the identification terminals set on each processing step, as well as the equipment operation data of the mechanical equipment used in each processing step; associate the simulated design parameters, the quality inspection results, and the equipment operation data with the electronic identifier, and construct the traceability database of the ring forging based on the association results.

6. The integrated intelligent process design and verification platform for ring forgings according to claim 4, characterized in that, The sensor layer is specifically used to receive the actual manufacturing data of the ring forging collected by the sensor and the dedicated detection unit after the current processing step is completed. The sensor and the dedicated detection unit are located on the mechanical equipment used in the current processing step.

7. The integrated intelligent process design and verification platform for ring forgings according to claim 6, characterized in that, The sensor layer is also used to integrate the equipment data of the mechanical equipment used in each processing step and the relevant process data of the ring forging in each processing step through the industrial Ethernet protocol, so as to build a full-process process-equipment data pool.

8. The integrated intelligent process design and verification platform for ring forgings according to claim 4, characterized in that, The actual manufacturing data includes at least the actual molding dimensions, mechanical property test results, actual temperature curves, actual deformation force curves, and actual grain sizes; The numerical simulation prediction results include at least the predicted molding size, the predicted mechanical properties, the predicted temperature curve, the predicted deformation force curve, and the predicted grain size; The output of the deviation evaluation model includes at least the difference between the actual molding size and the predicted molding size, the difference between the mechanical property test result and the mechanical property prediction result, the difference between the actual temperature curve and the predicted temperature curve, the difference between the actual deformation force curve and the predicted deformation force curve, and the difference between the actual grain size and the predicted grain size.

9. The integrated intelligent process design and verification platform for ring forgings according to claim 8, characterized in that, The quality management layer is further configured to automatically feed back the output result to the process management layer if the output result of the deviation assessment model meets the preset conditions.

10. A method for intelligent process design and verification of ring forgings, characterized in that, An integrated intelligent process design and verification platform for ring forgings as described in any one of claims 1-9, the platform comprising a process management layer and a big data analysis layer; the method comprising: The process management layer obtains the process route corresponding to the ring forging, which includes multiple processing steps. For each processing step, based on the processing mechanism model of the processing step, and according to the equipment operation parameters of the mechanical equipment used in the processing step, and the numerical simulation parameters when simulating the processing step, a dynamic mapping model corresponding to the processing step is constructed. The multiple processing steps include at least a heating step, a forging step, a rolling step, and a heat treatment step. When the processing step is a heating step, the process management layer is specifically used to construct a dynamic mapping model between the temperature field, thermal stress field, and phase ratio field and the heating curve and furnace atmosphere, based on the transient nonlinear heat conduction equation, radiation and convection heat transfer boundary condition model, and solid phase transformation dynamics model of the heating step. When the processing step is a forging step, the process management layer is specifically used to construct a strain model based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation, and damage model of the forging step. The process management layer is specifically used to construct a dynamic mapping model between the strain field, strain rate field, temperature field, rheological stress, and dynamic recrystallization fraction and grain size, and the press slide stroke, slide speed, forging force, and number of operations; when the processing step is a rolling step, the process management layer is specifically used to construct a dynamic mapping model between the strain field, temperature field, ring size change, and microstructure evolution, and the main roll speed, core roll feed speed, rolling time, and guide roll position, based on the plastic constitutive model, dynamic recrystallization model, heat conduction equation, damage model, and ring rolling kinematics and bite-in condition model of the rolling step; when the processing step is a heat treatment step, the process management layer is specifically used to construct a dynamic mapping model between the temperature-time history, static recrystallization fraction evolution, grain size evolution, precipitate fraction and size distribution, residual stress field, and final mechanical properties, and the heat treatment curve and furnace atmosphere control, based on the static recrystallization and grain growth model, precipitation kinetics model, phase transformation kinetics model, and heat conduction equation of the heat treatment step; Based on the virtual mirror of the production line of the process route, the big data analysis layer establishes data flow association rules across equipment processing steps using a workstation task algorithm. According to these data flow association rules, the current processing step is determined from the heating step, forging step, rolling step, and heat treatment step. Before the current processing step is executed, the actual execution data and real-time related status of the current processing step are input into the target dynamic mapping model corresponding to the current processing step, obtaining the current equipment running program parameters output by the target dynamic mapping model. Numerical simulation is then performed on the current processing step based on the current equipment running program parameters to generate the numerical simulation prediction results of the ring forging in the current processing step.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent process design and verification method for ring forgings as described in claim 10.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent process design and verification method for ring forgings as described in claim 10.

Images