Preparation method and system of low-cost high-strength superplastic rare earth magnesium alloy thin plate

Abstract

The invention relates to the field of intelligent manufacturing and optimization of metal materials, in particular to a preparation method and system of a low-cost high-strength superplastic rare earth magnesium alloy thin plate. The method comprises the following steps: acquiring component data of the Mg-RE-Zn-Zr alloy, and calculating an optimal ratio based on an artificial intelligence optimization algorithm; key elements are extracted, solid solution heat treatment is carried out, and microstructure parameters are obtained; in combination with sensing data, the extrusion temperature and the strain rate are optimized, and extrusion process parameters are generated; carrying out electron back scattering diffraction analysis, and extracting grain size data; based on the grain size data and the temperature feedback information, the rolling technology is optimized, and an optimal rolling deformation and temperature control curve is generated; an intelligent temperature control system is combined to adjust the rolling temperature in real time; and optimizing preorder process parameters in combination with an artificial intelligence model to generate a final optimization scheme. According to the method, process-structure-performance mapping is established through intelligent optimization, the material strength, the ductility and the superplasticity are improved, the cost is reduced, and the industrial application value is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing and optimization of metal materials, and in particular to a method and system for preparing low-cost, high-strength superplastic rare earth magnesium alloy thin plates. Background Art

[0002] Rare earth magnesium alloys are widely used in aerospace, automotive lightweighting, and electronic equipment due to their high specific strength, good superplasticity, and excellent corrosion resistance. However, the existing rare earth magnesium alloy thin sheet preparation technology has the following core problems: (1) Process parameter optimization relies on experience, resulting in poor preparation stability.

[0003] Currently, the preparation of magnesium alloy thin sheets usually relies on laboratory experiments and experience to adjust process parameters, such as alloy composition ratio, solution temperature, extrusion rate, rolling temperature, etc. This method has a long test cycle, high cost, and it is difficult to ensure preparation stability.

[0004] (2) The coupling of multi-dimensional process parameters makes it impossible to accurately predict material properties.

[0005] The performance of rare earth magnesium alloys is affected by multiple factors such as composition, processing path, temperature control, and deformation rate. There is a complex nonlinear coupling relationship between these parameters. Traditional single-factor optimization methods are difficult to systematically predict the final mechanical properties, resulting in difficulty in balanced optimization of superplasticity and strength.

[0006] (3) The lack of an intelligent closed-loop optimization system makes it difficult to achieve autonomous process adjustment.

[0007] The existing preparation process is mainly based on a fixed process window. When the material batch changes or the process fluctuates, re-testing and adjustment are often required. There is a lack of real-time monitoring and feedback optimization mechanism, and intelligent regulation cannot be performed during the preparation process. Summary of the Invention

[0008] The present application provides a method and system for preparing low-cost, high-strength, superplastic rare earth magnesium alloy thin sheets, to solve the problem of how to intelligently optimize and real-time control multi-dimensional process parameters such as alloy composition ratio, solution treatment, extrusion deformation, and rolling temperature control based on rare earth magnesium alloy composition data, microstructure parameters, heat treatment and deformation process data, combined with artificial intelligence models, to ensure that the preparation process of low-cost, high-strength, superplastic rare earth magnesium alloy thin sheets is stable and controllable, and to improve the tensile strength, elongation and superplasticity of the final product.

[0009] In order to solve the above technical problems, the present application provides a method for preparing a low-cost, high-strength superplastic rare earth magnesium alloy thin plate, comprising: Obtain the composition data of the Mg-RE-Zn-Zr alloy, calculate the optimal rare earth element ratio based on the artificial intelligence optimization algorithm, and generate the optimized alloy composition plan; Extracting key element ratios from the optimized alloy composition scheme, performing solution heat treatment, and obtaining microstructural parameters after solution treatment; Based on the microstructure parameters and combined with real-time sensor data, the temperature and strain rate during the extrusion process are intelligently adjusted to generate dynamic extrusion process parameters; Obtaining the dynamic extrusion process parameters, performing electron backscatter diffraction structure analysis on the extruded magnesium alloy sheet, generating microstructure refinement features, and extracting grain size data; Based on the grain size data and temperature feedback information, intelligently optimize a target strain rate rolling process to generate an optimal rolling deformation and temperature control curve, wherein the target strain rate rolling process involves a strain rate greater than a preset rate threshold; Obtain the temperature control curve and, in combination with the intelligent temperature control system, adjust the induction heating during the rolling process in real time to maintain the optimal processing temperature; Based on the optimal processing parameters, the mechanical property data of the magnesium alloy sheet is obtained, and the previous process parameters are optimized and iterated in combination with the artificial intelligence model to generate a final optimization solution; The method is based on the following optimization objective function: in, Indicates rolling temperature; Indicates the deformation of a single pass; Indicates the rolling line speed; Indicates the average grain size data of magnesium alloy sheet after final rolling; represents the final dynamic recrystallization ratio; Indicates the optimized target temperature; 、 、 Represents the weight coefficient.

[0010] Furthermore, the step of obtaining the composition data of the Mg-RE-Zn-Zr alloy, calculating the optimal rare earth element ratio based on an artificial intelligence optimization algorithm, and generating an optimized alloy composition scheme includes: Extract the experimental data of historically prepared Mg-RE-Zn-Zr alloys, including the ratio information of Gd, Nd, Zn, Zr rare earth and trace elements, and form an alloy composition database; Analyzing the alloy composition database, calculating the effects of different ratios on mechanical properties, superplasticity, and cost based on the artificial intelligence optimization algorithm, generating the optimization objective function, and constructing an alloy composition optimization model; Based on the optimization objective function, the proportion of alloy elements is adjusted to generate an optimal alloy formula that meets the requirements of high strength and superplasticity, and the optimized alloy composition scheme is output.

[0011] Furthermore, extracting the key element ratios from the optimized alloy composition scheme, performing solution heat treatment, and obtaining the microstructure parameters after solution treatment includes: Extracting the key element ratios of the optimized alloy composition scheme, determining the solid solution temperature range of the rare earth elements Gd, Nd, Zn, and Zr, and generating solid solution treatment parameters; According to the solution treatment parameters, the Mg-RE-Zn-Zr alloy is subjected to a solution heat treatment in the range of 480° C. to 545° C. and maintained for 8 to 36 hours to obtain a uniform solution structure; The phase distribution after solid solution is detected by scanning electron microscopy (SEM) and energy dispersive spectroscopy (EDS), and the microstructure parameter data after solid solution is generated and transferred to the extrusion process module.

[0012] Furthermore, based on the microstructure parameters and in combination with real-time sensor data, the temperature and strain rate in the extrusion process are intelligently adjusted to generate dynamic extrusion process parameters, including: Obtaining the microstructure parameters after the solid solution, combining the real-time temperature, stress, and strain sensor data, and processing the heating temperature of the extrusion process, the mold preheating state, and the extrusion speed; Optimizing the extrusion process parameters, calculating the optimal extrusion temperature range and the optimal extrusion rate based on finite element simulation (FEM), and generating the dynamic extrusion process parameters; Based on the dynamic extrusion process parameters, the extrusion process is adjusted, and precise temperature control and rate regulation are performed using an induction heating system and a real-time strain monitoring device to obtain a magnesium alloy thin plate with uniform structure.

[0013] Furthermore, the dynamic extrusion process parameters are obtained, and electron backscatter diffraction structure analysis is performed on the extruded magnesium alloy sheet to generate microstructure refinement features and extract grain size data, including: Obtain the microstructure data of the extruded magnesium alloy sheet, scan the sample using an EBSD analysis system, and obtain grain size data and orientation distribution microstructure data; Analyzing the organizational data, calculating average grain size data and dynamic recrystallization ratio after extrusion, and generating the microstructural refinement characteristics; The grain size data is extracted, the superplasticity trend is analyzed based on the microstructure refinement characteristics, and the trend data is transmitted to a high strain rate rolling optimization module to guide the setting of rolling process parameters.

[0014] Furthermore, the target strain rate rolling process is intelligently optimized based on the grain size data and temperature feedback information to generate an optimal rolling deformation and temperature control curve, including: Acquire the grain size data and the temperature feedback information, form a material property database before rolling based on the microstructure data analyzed by EBSD, and combine the roll temperature and deformation history data; Analyzing the material property database, calculating optimal high strain rate rolling parameters based on an artificial intelligence model, including single-pass deformation, optimal rolling temperature and linear speed, and generating the temperature control curve; Based on the temperature control curve, the rolling process is optimized, and the induction heating system of the rolling process is regulated so that the rolling deformation and temperature are controlled within the optimized range.

[0015] Furthermore, the acquisition of the temperature control curve and the combination with the intelligent temperature control system to adjust the induction heating during the rolling process in real time to maintain the optimal processing temperature include: Obtain the temperature control curve and real-time processing temperature data, collect the roll temperature and rolling temperature based on the intelligent temperature sensor, and perform matching analysis with the optimized temperature control curve; The rolling temperature is intelligently adjusted. When the actual processing temperature deviates from the optimized temperature control curve, the power output of the induction heating system is adjusted to maintain the processing temperature within the optimal range.

[0016] Furthermore, based on the optimal processing parameters, the mechanical property data of the magnesium alloy sheet is obtained, and the preceding process parameters are optimized and iterated in combination with the artificial intelligence model to generate a final optimization solution, including: Obtaining the optimal processing parameters and plate performance data, and extracting the tensile strength, elongation, and microhardness performance indicators of the final magnesium alloy plate based on tensile testing, hardness testing, and EBSD analysis methods; Based on artificial intelligence prediction models, the impact of processing parameters on final performance is analyzed, optimization targets are updated, and preceding process parameters are adjusted; Generate the final optimization plan, form the optimal process path for the preparation of rare earth magnesium alloy plates, and use it to guide the next round of production process optimization.

[0017] Furthermore, the training process of the artificial intelligence model includes: Obtain historical process parameters and material properties data to construct a training dataset containing alloy composition, heat treatment parameters, deformation parameters, and final mechanical properties; Using an artificial intelligence optimization method based on a deep neural network (DNN) or a support vector regression (SVR) model to model the training data set and extract a mapping relationship between alloy composition and final mechanical properties; A genetic algorithm (GA) or a Bayesian optimization (BO) method is used to optimize the parameters of the artificial intelligence model to generate an artificial intelligence process optimization model for prediction and optimization.

[0018] Furthermore, the final optimization solution is used for industrial production control, and the method further includes: Generate process specification files containing optimized process parameters and store them in the database for industrial production line access; During the production process, process parameters are monitored in real time and dynamically adjusted based on the final optimization plan, including adjusting key process parameters such as alloy ratio, solution temperature, extrusion rate, rolling temperature and deformation amount; Through the intelligent control system, the temperature, pressure and deformation rate of the production equipment are automatically adjusted to match the optimized process path, and the feedback control mechanism is used to iteratively update the process optimization plan.

[0019] The following are its main beneficial effects: (1) Through artificial intelligence optimization algorithms, accurate optimization of alloy composition and process parameters is achieved to improve the overall performance of the material. This application establishes a correlation model between alloy composition, microstructure, processing technology, and mechanical properties based on artificial intelligence optimization algorithms, and iteratively optimizes rare earth elements, heat treatment processes, and deformation process parameters with different ratios. Compared with the traditional parameter adjustment method that relies on experimental experience, it can accurately predict the optimal process solution. This method effectively improves the tensile strength, elongation, and superplasticity of magnesium alloy thin plates, ensuring the feasibility of the material's application in high-performance structural parts.

[0020] (2) Combining real-time sensor monitoring with data-driven optimization to achieve intelligent control of process parameters and improve production process stability. During the extrusion and rolling process, this application combines real-time temperature, strain rate, dynamic recrystallization ratio and other sensor data to intelligently adjust processing parameters, so that the production process no longer relies on a fixed process window, but is based on dynamic process parameter optimization to achieve precise control. Compared with traditional fixed temperature control and manual adjustment methods, this method can reduce process fluctuations, improve the uniformity of the microstructure of magnesium alloy sheets, and enhance superplastic processing performance.

[0021] (3) Construct a closed-loop optimization control system to achieve iterative process optimization and improve industrial production efficiency. This application constructs an artificial intelligence-based closed-loop optimization control system. The final mechanical property data is obtained through EBSD microstructure analysis, tensile testing, hardness testing, etc., and iterative adjustments are made in combination with the optimization model to form a new round of optimal processing technology solutions. Compared with the traditional method that relies on experience adjustment, this method can reduce experimental costs, shorten the R&D cycle, and improve the stability of the industrial production process, making the magnesium alloy thin plate preparation process have a higher level of automation and intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of a method for preparing a low-cost, high-strength, superplastic rare earth magnesium alloy thin plate provided in an embodiment of the present application; Figure 2 This is a schematic diagram of the results of a method for preparing a low-cost, high-strength superplastic rare earth magnesium alloy thin plate provided in an embodiment of the present application; Figure 3 A schematic diagram of a microstructure change provided in an embodiment of the present application; Figure 4 The second schematic diagram of the results of a method for preparing a low-cost, high-strength superplastic rare earth magnesium alloy thin plate provided in an embodiment of the present application; Figure 5 This is a structural block diagram of a system for preparing a low-cost, high-strength superplastic rare earth magnesium alloy thin plate provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0024] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0025] Example 1: Reference Figure 1 , is a schematic flow chart of a method for preparing a low-cost, high-strength superplastic rare earth magnesium alloy thin plate provided in an embodiment of the present application. The process may at least include S100-S700: S100. Obtain composition data of the Mg-RE-Zn-Zr alloy, calculate the optimal rare earth element ratio based on an artificial intelligence optimization algorithm, and generate an optimized alloy composition solution.

[0026] S200: Extract the key element ratios from the optimized alloy composition scheme, perform solid solution heat treatment, and obtain the microstructure parameters after solid solution.

[0027] S300, based on microstructure parameters and combined with real-time sensor data, intelligently adjusts the temperature and strain rate during the extrusion process to generate dynamic extrusion process parameters.

[0028] S400, obtaining dynamic extrusion process parameters, performing electron backscatter diffraction structure analysis on the extruded magnesium alloy sheet, generating microstructure refinement features, and extracting grain size data.

[0029] S500. Based on the grain size data and the temperature feedback information, the target strain rate rolling process is intelligently optimized to generate an optimal rolling deformation and temperature control curve. The strain rate involved in the target strain rate rolling process is greater than a preset rate threshold.

[0030] S600 obtains the temperature control curve and, combined with the intelligent temperature control system, makes real-time adjustments to the induction heating during the rolling process to maintain the optimal processing temperature.

[0031] S700, based on the optimal processing parameters, obtains the mechanical properties data of the magnesium alloy sheet, and combines the artificial intelligence model to iteratively optimize the previous process parameters to generate the final optimization solution.

[0032] The above method is based on the following optimization objective function: in, Indicates rolling temperature; Indicates the deformation of a single pass; Indicates the rolling line speed; Indicates the average grain size data of magnesium alloy sheet after final rolling; represents the final dynamic recrystallization ratio; Indicates the optimized target temperature; 、 、 Represents the weight coefficient.

[0033] Wherein, the thinness of the above-mentioned magnesium alloy plate is less than a preset thinness threshold. At this time, the magnesium alloy plate becomes a magnesium alloy thin plate.

[0034] Optionally, S100 includes at least S110-S130: S110. Extracting experimental data of historically prepared Mg-RE-Zn-Zr alloys, including information on the ratios of Gd, Nd, Zn, Zr rare earths, and trace elements, and forming an alloy composition database.

[0035] Obtain historical data, specifically, extract the composition data of Mg-RE-Zn-Zr alloys prepared in previous experiments, which includes but is not limited to the mass fractions of Gd, Nd, Zn, and Zr. 、 、 、 , and the overall mass fraction of the alloy .

[0036] Data preprocessing, further, cleans and filters the historical experimental data, removes abnormal data, and ensures data quality. For alloy samples under different experimental conditions, obtain their corresponding tensile strength , elongation after fracture , recrystallization ratio , and normalize it for subsequent modeling and calculation.

[0037] Construct an alloy composition database based on the extracted rare earth magnesium alloy element ratio data and performance test data. Each data record in the database is as follows: in, Indicates the A set of experimental data is collected, and the alloy composition database will serve as the input data source for AI optimization calculations.

[0038] S120. Analyze the alloy composition database, calculate the impact of different ratios on mechanical properties, superplasticity and cost based on the AI ​​optimization algorithm, generate the optimization objective function, and construct an alloy composition optimization model.

[0039] Construct an objective function. Specifically, based on the above alloy composition database, model the impact of different rare earth element ratios on the mechanical properties, superplasticity and cost of the material. Set the optimization goal: Improved tensile strength: Maximized tensile strength ; Optimizing superplasticity: maximizing elongation after fracture ; Reduce costs: Minimize the sum of the mass fractions of high-value rare earth elements (Gd, Nd).

[0040] Furthermore, the objective function for alloy performance optimization is established: in, 、 and Represents the weight coefficient, which is determined by regression fitting of experimental data to balance the influence of strength, plasticity and cost.

[0041] Optimize computing and machine learning model training, randomly extract from the database Group samples as training set , build a neural network model : Optimize by minimum mean square error (MSE): in, and are the true values ​​measured experimentally, and is the predicted value of the neural network. The neural network weights are optimized iteratively to make the predicted value closest to the true value.

[0042] Calculate the optimal ratio and further optimize the objective function based on the alloy performance , using genetic algorithm to search for the optimal alloy element ratio: Initialize the population and randomly generate alloy composition vectors ; Calculate fitness using Predicting each individual and , and bring it into the alloy performance optimization objective function ; Perform cross-mutation to update alloy composition; Iterative convergence finally results in the optimized alloy composition ratio in, 、 、 、 They respectively represent the mass fraction of each element in the magnesium-rare earth-zinc-zirconium alloy determined after optimization calculation, which is used to guide the temperature range and treatment parameters of the solution treatment.

[0043] S130. Based on the optimization objective function, adjust the proportion of alloy elements to generate the best alloy formula that meets the requirements of high strength and superplasticity, and output the optimized alloy composition plan.

[0044] Adjust the alloy element ratio. Specifically, the optimal alloy ratio obtained based on the optimization calculation is: Adjust alloy smelting parameters to ensure that the mass fraction of alloy elements in actual production strictly conforms to the calculated results.

[0045] Generate an optimized alloy composition scheme. Further, combine the calculated optimal alloy ratio with the experimental verification results to form a standardized alloy composition scheme, and store it in the alloy composition database for subsequent alloy preparation process call.

[0046] The data is transferred to the solution treatment module. Specifically, the optimized alloy composition scheme is used as input data for S210 solution treatment parameter optimization to ensure that subsequent heat treatment steps are performed based on the optimized composition scheme.

[0047] Optionally, S200 includes at least S210-S230: S210. Extract the key element ratios of the optimized alloy composition scheme, determine the solid solution temperature range of rare earth elements such as Gd, Nd, Zn, and Zr, and generate solid solution treatment parameters.

[0048] Extract optimized alloy composition data, specifically, the optimal alloy ratio calculated from S130: .

[0049] Calculate the solid solution temperature range and further calculate the solid solubility of different elements based on the optimal alloy ratio and temperature The solution temperature range is determined by the following empirical equation: in: Indicates the optimal solution temperature of the alloy; 、 、 、 、 represents an empirical constant, which can be obtained by fitting experimental data.

[0050] Generate solution treatment parameters. Further, based on the experimental database, set the alloy solution temperature range as follows: The upper limit of 545°C is determined by the maximum solid solubility of rare earth elements, and the lower limit of 480°C is determined by the structural stability requirements of the magnesium matrix.

[0051] Combined with the alloy characteristics, the solution time range is further determined: in: Represents the time of solution treatment; this time range is fitted according to experimental data to ensure the uniformity of the structure and reduce the heterogeneity of the precipitated phase.

[0052] Generated solution treatment parameters : This parameter set will be used to guide the S220 solution heat treatment.

[0053] S220. Perform solution heat treatment according to solution treatment parameters, subjecting the Mg-RE-Zn-Zr alloy to solution heat treatment at a temperature in the range of 480° C. to 545° C. and maintaining the temperature for 8 to 36 hours to obtain a uniform solution structure.

[0054] Loading solution treatment parameters, specifically, based on S210 calculation , set the target temperature of alloy solution in the control system and holding time , and pre-treat the magnesium-rare earth-zinc-zirconium alloy.

[0055] The heating process is performed, and further, the alloy is heated in a high temperature furnace so that the temperature is increased at the following rate: in: Indicates the heating rate in °C / min; Determined by experimental data, it is usually controlled at 5-10°C / min to prevent abnormal tissue growth or excessive thermal stress.

[0056] In the solution holding stage, when the temperature reaches After that, keep the time , so that the second phase in the alloy is fully dissolved. During this period, the precipitated phase in the alloy structure and Gradually dissolve into the magnesium matrix and reduce the heterogeneity of the interface precipitates.

[0057] The reaction process can be expressed as: in: represents the magnesium matrix; Represents the rare earth element precipitation phase in magnesium alloy; Represents the uniform phase after solid solution.

[0058] Rapid cooling, further, after the solution treatment is completed, water cooling (WQ) or air cooling (AC) is used for rapid cooling to prevent secondary precipitation. Cooling rate Set to: To ensure uniformity in the organization and reduce grain boundary precipitation.

[0059] S230, obtaining microstructure parameters after solid solution, detecting the phase distribution after solid solution by scanning electron microscopy (SEM) and energy dispersive spectroscopy (EDS), generating microstructure parameter data after solid solution, and transmitting the data to the extrusion process module.

[0060] The microstructure parameter data after solution treatment were extracted. Specifically, after the solution treatment was completed, samples were cut from the magnesium alloy plates, and the solution structure was observed using a scanning electron microscope (SEM).

[0061] Analyze grain orientation and extract grain refinement parameters using electron backscatter diffraction (EBSD) : in: Indicates the average grain size data after solid solution; Indicates the Crystal size data of each grain; Indicates the total number of grains detected.

[0062] Furthermore, EDS energy spectrum analysis was used to determine the rare earth element distribution of the alloy after solid solution and calculate the solid solution efficiency: in: is the solid solution efficiency; is the rare earth element content after solid solution; is the theoretical element content in the optimized alloy composition scheme.

[0063] Transfer data to the extrusion process module, and further, the microstructure parameters after solution and The samples are transferred to S300 extrusion process optimization to calculate the extrusion rate and temperature parameters to ensure uniformity of the tissue during subsequent processing.

[0064] Optionally, S300 includes at least S310-S330: S310, obtaining microstructure parameters, combining real-time temperature, stress, and strain sensing data, and performing data processing on the heating temperature of the extrusion process, the mold preheating state, and the extrusion speed.

[0065] Extract the microstructure parameters after solid solution. Specifically, the microstructure parameters after solid solution calculated from S230 include: Average grain size data after solution ; Solid solution efficiency ; Precipitation phase distribution data .

[0066] The microstructure parameters after solid solution are used to guide the temperature control and deformation rate optimization of the extrusion process, ensuring that the extrusion process can maximize grain refinement while avoiding the generation of uneven structure.

[0067] Collect real-time sensor data. Furthermore, during the extrusion process, embedded high-temperature sensors and strain monitoring systems are used to obtain the following real-time process parameters: mold temperature ; Alloy billet temperature ; Extrusion speed Extrusion pressure ; strain rate .in: Indicates the real-time temperature of the mold; Indicates the preheating temperature of the alloy billet before extrusion; Indicates the moving speed of the extrusion rod; Indicates the total pressure applied during the extrusion process; Represents the strain rate experienced by the alloy during extrusion.

[0068] Data normalization and processing, further, based on the collected real-time sensor data and the microstructure parameters after solid solution, the actual grain growth factor is calculated : in: represents the material constant; represents the activation energy of grain growth; represents the gas constant; Indicates alloy billet temperature; represents the strain rate; represents the strain rate sensitivity index.

[0069] By calculation , it can be determined whether the extrusion parameters need to be adjusted to optimize the final microstructure refinement characteristics S320: Intelligently optimize extrusion process parameters, calculate the optimal extrusion temperature range and optimal extrusion rate based on finite element simulation analysis (FEM), and generate dynamic extrusion process parameters.

[0070] Construct a finite element analysis (FEM) model for the extrusion process. Specifically, based on the process parameters obtained in S310, a finite element analysis (FEM) model for the extrusion process is established, and the material constitutive relationship is set: in: represents the flow stress; Indicates the material strengthening coefficient; represents the effective plastic strain; represents the strain hardening exponent; represents the thermal activation energy; represents the gas constant; Indicates the material temperature.

[0071] Calculate the optimal extrusion temperature range. Further, use the FEM model to calculate the temperature-strain rate relationship curve to determine the optimal extrusion temperature range: in, It indicates the optimal extrusion temperature range, which enables the material to maintain high plasticity and reduce flow stress during the extrusion process.

[0072] Calculate the optimal extrusion rate. Further, calculate the optimal extrusion rate within the determined optimal extrusion temperature range: in: Indicates the optimal extrusion speed; Indicates the length of the alloy billet; Indicates the optimal extrusion time.

[0073] Combined with finite element calculation, the dynamic extrusion process parameters are finally generated: in, Indicates the optimal extrusion pressure.

[0074] S330. Based on dynamic extrusion process parameters, adjust the extrusion process, use the induction heating system and real-time strain monitoring device to perform precise temperature control and rate regulation to obtain magnesium alloy thin plates with uniform structure.

[0075] Load dynamic extrusion process parameters, specifically, the optimal extrusion process parameters calculated based on S320 , set the real-time control target of the extrusion process: Mold preheating temperature: set to ; Induction heating control: ensures that the blank is kept in the optimal temperature range; Real-time speed adjustment: Set the extrusion rod moving speed to .

[0076] Dynamic adjustment of the extrusion process, further, real-time monitoring of the strain rate during the extrusion process and flow stress , and adjust the extrusion parameters: in, Calculated by the real-time temperature control system to compensate for temperature fluctuations.

[0077] Perform precise temperature and rate regulation, and further, during the extrusion process: If the strain rate is monitored in real time Beyond the optimal range, adjust ; If the mold temperature In case of deviation, the intelligent induction heating system is used for real-time compensation; If the flow stress Too large, reduce appropriately , in order to improve the deformation uniformity of the material.

[0078] Through the above intelligent adjustment, a magnesium alloy thin sheet with uniform structure is achieved, and the superplastic properties of the material are ensured to meet the design requirements.

[0079] Optionally, S400 includes at least S410-S430: S410. Obtain the microstructure data of the extruded magnesium alloy sheet. Use the EBSD (electron backscatter diffraction) analysis system to scan the sample and obtain microstructure data such as grain size data and orientation distribution.

[0080] Extract the microstructure information of the magnesium alloy sheet after extrusion. Specifically, a sample was cut from the magnesium alloy sheet after S330 extrusion, and the sample was mechanically polished and electrolytically etched to obtain a clear grain boundary structure. The sample preparation process includes: Use SiC sandpaper to grind to 4000# step by step; Polishing with aluminum oxide suspension to obtain a stress-free surface; Electrolytic etching is performed in an ethanol-acetic acid-water solution to reveal the grain boundaries.

[0081] EBSD system scanning analysis. Further, the sample was scanned in the EBSD system equipped with a scanning electron microscope (SEM) to obtain grain size data. and orientation distribution data The acquisition parameters of the EBSD system are as follows: Accelerating voltage: 20 kV; Step size: 0.5µm; Scanning area: 100µm × 100µm.

[0082] in: Indicates the grain size data after extrusion; Represents the grain orientation distribution and reflects the preferred orientation of the structure (Texture).

[0083] Data storage and transmission, further, the EBSD data is stored in the database and transmitted to the S420 structure data analysis module to calculate the dynamic recrystallization ratio and microstructure refinement characteristics.

[0084] S420, analyzing the organizational data, calculating the average grain size data and dynamic recrystallization ratio after extrusion, and generating microstructure refinement feature data.

[0085] Calculate the average grain size data after extrusion, specifically, based on the data collected by S410 Data, calculate the average grain size data: in: It represents the average size data of the grains after extrusion; Indicates the Measured grain size data; Indicates the total number of grains measured.

[0086] Calculate the dynamic recrystallization ratio and further analyze the dynamic recrystallization (DRX) area ratio based on EBSD data: in: represents the dynamic recrystallization ratio; represents the area of ​​the recrystallized region; Indicates the total area of ​​the scanned region.

[0087] Generate microstructure refinement feature data, further, combine and , defining the microstructure refinement factor : in: It reflects the degree of grain refinement, and the larger the value, the higher the degree of microstructure refinement; This parameter will be used in S430 for superplasticity trend analysis and rolling process optimization.

[0088] S430: Extract grain size data, analyze superplasticity trends based on microstructure refinement characteristics, and transmit trend data to the high strain rate rolling optimization module to guide the setting of rolling process parameters.

[0089] Superplasticity trend analysis, specifically, based on S420 calculations and , combined with literature data, a superplasticity prediction model is established: in: represents the predicted superplastic elongation after fracture; represents the reference grain size data; 、 、 represents the experimental fitting constant.

[0090] Adjust the rolling process parameters, further, according to the calculation of S430 Value, set the initial parameters of high strain rate rolling: Rolling temperature range : Single pass deformation : Rolling speed : The data is transferred to the rolling optimization module, and further, the calculated 、 、 Transferred to S500 to optimize the high strain rate rolling process and ensure the stability of superplastic formation.

[0091] Optionally, S500 includes at least S510-S530: S510, obtaining grain size data and temperature feedback information, and forming a material property database before rolling based on the microstructure data analyzed by EBSD and combined with the roll temperature and deformation history data.

[0092] Extract the post-extrusion grain size data, specifically, the grain refinement feature data calculated from S430, including: Average grain size data after extrusion ; Dynamic recrystallization ratio ; Superplasticity predicted elongation .

[0093] in, Indicates the degree of grain refinement after extrusion. Indicates tissue homogeneity, The above data are used to guide the setting of high strain rate rolling parameters.

[0094] Obtain rolling process historical data. Further, on the rolling equipment, collect the following historical data: Roll temperature ; Single pass deformation ; Rolling line speed .

[0095] in, represents the temperature feedback under different rolling conditions, Represents historical deformation data, Represents the strain rate under different rolling conditions.

[0096] A database of material properties before rolling is formed. Furthermore, the grain size data and historical rolling process parameters are stored in the database to establish a data set: in, It will be used to optimize the S520 rolling process to ensure that the process parameters of high strain rate rolling reasonably match the microstructure evolution trend.

[0097] S520. Analyze the material properties database, calculate the optimal high strain rate rolling parameters based on the artificial intelligence model, including single-pass deformation, optimal rolling temperature and line speed, and generate a temperature control curve.

[0098] Construct the rolling process optimization objective function. Specifically, based on the data collected by S510 Data, key parameters for optimizing high strain rate rolling: Maximize grain refinement: Minimize the grain size data after rolling ; Ensuring superplastic stability: Optimizing the dynamic recrystallization ratio ; Reduce the risk of material cracking during rolling: constrain rolling temperature and deformation.

[0099] Furthermore, the optimization objective function is constructed: in: 、 、 represents the optimization variable; Obtained from EBSD analysis after rolling; Obtained by dynamic recrystallization calculation; Indicates the historical optimal rolling temperature range; 、 、 Represents the weight coefficient.

[0100] The optimal rolling parameters are calculated and then, based on the optimization objective function, the genetic algorithm (GA) is used to search for the optimal parameters: in, represents the optimal rolling temperature, represents the optimal deformation, Indicates the optimal rolling speed.

[0101] Generate a temperature control curve. Further, combine the optimal parameters to calculate the temperature control curve during the rolling process: in: Indicates rolling time Temperature below is the temperature control coefficient; Reflects the temperature attenuation characteristics during the rolling process.

[0102] This temperature control curve will be used for S530 rolling temperature control to ensure temperature stability.

[0103] S530. Based on the temperature control curve, optimize the rolling process and regulate the induction heating system of the rolling process to ensure that the rolling deformation and temperature are controlled within the optimized range to improve the superplasticity of the material.

[0104] Load the optimized rolling process parameters, specifically, based on the S520 calculation 、 、 Parameters, setting rolling equipment: Rolling temperature setting ; Single pass deformation setting ; Rolling speed setting .

[0105] The induction heating system is controlled in real time. Furthermore, the rolling temperature is monitored in real time during the rolling process. And perform temperature compensation: in: Indicates the rolling temperature after compensation; Indicates the temperature regulation coefficient.

[0106] Ensure the stability of the rolling process. Furthermore, during the rolling process: If the temperature Deviation , then adjust the induction heating system power; If the rolling speed Deviation , then adjust the roller speed; If the dynamic recrystallization ratio If the value is lower than the threshold, the deformation compensation is increased.

[0107] Through the above-mentioned intelligent optimization, precise control of high strain rate rolling is achieved to ensure the superplastic formation of magnesium alloy thin plates.

[0108] Optionally, S600 includes at least S610-S630: S610: Acquire the temperature control curve and real-time processing temperature data, collect the roller temperature and rolling temperature based on the intelligent temperature sensor, and perform matching analysis with the optimized temperature control curve.

[0109] Extract optimized temperature control curve data, specifically, the temperature control curve calculated from S520: in: Represents the rolling process Theoretical temperature at the moment; represents the optimal rolling temperature; represents the temperature control coefficient; Indicates the temperature decay characteristics during rolling.

[0110] This curve is used to guide the real-time adjustment of temperature during the rolling process to ensure that the material is deformed within the optimal processing temperature range.

[0111] Acquire real-time temperature data. Furthermore, based on the intelligent temperature sensor, collect the following real-time data: Roll temperature ; Rolling zone temperature ; Ambient temperature .

[0112] in: Indicates the operating temperature of the rolling equipment; Indicates the actual temperature of the material in the rolling area; Indicates the external ambient temperature to compensate for the influence of external factors.

[0113] Match and analyze the temperature control curve. Further, match and analyze the collected real-time temperature data with the optimized temperature control curve to calculate the temperature deviation: in: Indicates the deviation of the current material temperature from the optimal temperature; if , indicating that the material temperature is too high; like , indicating that the material temperature is too low.

[0114] The calculation results will be used for intelligent adjustment of the S620 rolling temperature to ensure that the temperature is always maintained in the optimal range.

[0115] S620, intelligently adjusts the rolling temperature. When the actual processing temperature deviates from the optimized temperature control curve, the power output of the induction heating system is automatically adjusted to maintain the processing temperature in the optimal range. Calculate the temperature adjustment target, specifically, based on the temperature deviation calculated in S610 , determine the target value for adjusting the induction heating system power: in: Indicates the adjusted induction heating power; Indicates the initially set heating power; Indicates the temperature compensation coefficient.

[0116] This formula ensures that the heating power is increased when the temperature is below the optimal temperature and is decreased when the temperature is above the optimal temperature.

[0117] Dynamically adjust the induction heating system. Furthermore, use the temperature control system to adjust the induction heating power in real time: like , then increase To increase the material temperature; like , then reduce To reduce the material temperature.

[0118] By dynamically adjusting the heating system, precise temperature control can be achieved during the rolling process, ensuring that the processing temperature is always maintained in the optimal range.

[0119] Feedback temperature adjustment results, further, after the temperature adjustment, re-collect real-time temperature data , and calculate the new temperature deviation : like If it is still greater than the set threshold, continue to adjust , until the optimized temperature control curve requirements are met.

[0120] This data will be used by S630 to implement intelligent temperature control strategies to ensure temperature stability throughout the rolling process.

[0121] S630, implements intelligent temperature control strategy, combined with real-time feedback mechanism, to dynamically adjust the heating and cooling systems during the rolling process to ensure the microstructural uniformity of the final product.

[0122] Establish a real-time feedback temperature control mechanism. Specifically, build an intelligent temperature control feedback mechanism based on the temperature adjustment data of S620: collection And calculate the temperature error ; Adjust heating power To compensate for temperature deviation; After monitoring adjustment To verify the adjustment effect.

[0123] Dynamically adjust heating and cooling systems. Further, combined with real-time feedback data, dynamically adjust heating and cooling systems: when (temperature below optimum): Increase the induction heating power to increase the temperature; Reduce the cooling fluid supply to reduce the heat dissipation rate.

[0124] when (temperature above optimum): Reduce induction heating power and heat input; Increase the cooling fluid supply and improve the heat dissipation rate.

[0125] Through the above dynamic adjustment, the rolling temperature is ensured to be stable in the optimal range, avoiding the adverse effects of temperature fluctuations on the microstructure.

[0126] Optimize microstructural uniformity. Further, after rolling is completed, the microstructural uniformity of the material is evaluated based on the final processing temperature data: in: Indicates the grain uniformity index; Indicates the Grain size data; Indicates the average size data of the final grains.

[0127] like If the set threshold is exceeded, the process goes back to S620 to perform further temperature optimization to improve tissue uniformity.

[0128] Optionally, S700 includes at least S710-S730: S710. Obtain the optimal processing parameters and plate performance data, and extract the final magnesium alloy plate's tensile strength, elongation, microhardness and other performance indicators based on tensile tests, hardness tests, EBSD analysis and other methods.

[0129] Extract the optimal processing parameters. Specifically, extract the following key parameters from the final rolling process data transmitted by S630: Final processing temperature ; Final rolling deformation ; Rolling rate .

[0130] in: Indicates the temperature of the plate at the completion of rolling; Indicates the final total deformation; Indicates the rolling speed of the final process.

[0131] The mechanical properties of the plate were tested. Furthermore, in a laboratory environment, the plate was subjected to mechanical testing according to ASTM standards to obtain the following indicators: tensile strength ; Yield strength ; Elongation ; Microhardness .

[0132] in: Measured by tensile test; Calculated by the inflection point of the stress-strain curve; Calculated by the strain amount before tensile fracture; Measured by Vickers hardness tester.

[0133] Obtain microstructure data. Further, use the EBSD (Electron Backscatter Diffraction) analysis system to scan the microstructure of the final product and extract: Final grain size data ; Dynamic recrystallization ratio ; Texture distribution parameters .

[0134] in: Indicates the average size data of the final grains; represents the dynamic recrystallization ratio; Indicates the preferred orientation distribution of the texture.

[0135] The mechanical properties data and microstructure data will be used for S720AI optimization iterative analysis to optimize the preceding processing parameters.

[0136] S720: Iterate and optimize the processing parameters and performance data. Based on the AI ​​prediction model, analyze the impact of the processing parameters on the final performance, update the optimization target, and adjust the previous process parameters.

[0137] Build an AI optimization prediction model. Specifically, build an AI prediction model based on the experimental data collected by S710: in: Represents the AI ​​prediction model; input parameters Indicates the optimal processing parameters; output parameters Indicates the mechanical properties and organizational characteristics of the plate.

[0138] Furthermore, the optimization goal is: in: The weight coefficient that represents the effect of microstructure on performance; This optimization objective balances strength, plasticity, and grain size data to improve the overall performance of the material.

[0139] Calculate the optimal pre-process parameters. Further, based on the AI ​​prediction model, calculate the optimized pre-process parameters: in: represents the optimal rolling deformation; represents the optimal rolling temperature; represents the optimal rolling rate.

[0140] Calculated 、 and It will be used in S730 to generate the final optimization plan to adjust the next round of process parameters.

[0141] Update the optimization target. Further, adjust the processing target based on the process optimization results calculated by the AI ​​prediction model: like If it is lower than the design requirement, increase To improve strength; like If the superplasticity requirement is lower than the requirement, then optimize To increase dynamic recrystallization; like If too large, adjust To improve grain refinement.

[0142] The optimization iteration data will be used in S730 to form the final optimization plan to ensure the continuous optimization of process parameters.

[0143] S730. Generate the final optimization plan. Based on the results of the optimization iteration, form the optimal process path for the preparation of rare earth magnesium alloy plates, and use it to guide the next round of production process optimization.

[0144] Summarize the optimization data, specifically, the optimized process parameters calculated based on S720: in: Indicates the final optimized process path; this parameter set will serve as the reference process plan for the next round of production.

[0145] The optimal process path is formed. Furthermore, the AI ​​model is combined with the predicted optimization results to formulate the final processing flow: Setting optimal solution heat treatment parameters ; Setting optimal extrusion process parameters ; Setting optimal high strain rate rolling parameters .

[0146] Guide the new round of production process optimization, and further, the final optimization plan Feedback to the process database updates the control parameters of production equipment and forms a closed-loop optimization system: in: Represents the data from the previous optimization iteration.

[0147] This path is used in the new round of production and manufacturing to ensure the continuous optimization of the rare earth magnesium alloy sheet preparation process.

[0148] See also Figure 2 By using the preparation method of the low-cost, high-strength superplastic rare earth magnesium alloy sheet provided in this application, the obtained magnesium alloy sheet has a tensile strength of 320 MPa at room temperature (25°C) and still maintains a tensile strength of 200 MPa under high temperature (300°C), reflecting good room temperature mechanical properties and heat resistance stability, and is suitable for structural parts application scenarios with a maximum operating temperature close to 300°C.

[0149] See also Figure 3 After the above preparation method is optimized by extrusion and high strain rate rolling, the microstructure of the material is significantly refined, from the original average grain size data of about 30μm to about 2.5μm, indicating that the present application has achieved efficient dynamic recrystallization and grain homogenization in terms of organizational control.

[0150] See also Figure 4 The rare earth magnesium alloy sheet prepared by the above method exhibits excellent superplastic behavior in the temperature range of 350°C to 450°C, and its elongation can reach 200% to 1100%, which can meet the hot forming processing requirements of complex precision components, reflecting the engineering adaptability of this application in high-performance magnesium alloy forming applications.

[0151] The key innovations of this application include: (1) Process parameter calculation model based on artificial intelligence optimization algorithm. This application uses artificial intelligence optimization algorithm and combines finite element analysis (FEM) to model and optimize multiple process parameters such as solid solution, extrusion, and rolling. It breaks through the limitations of traditional reliance on experiments and experience adjustments and achieves accurate prediction and optimization of alloy properties.

[0152] (2) Dynamic process adjustment method based on real-time sensor data. This application introduces real-time sensor data such as temperature, strain rate, and dynamic recrystallization ratio to intelligently control processing parameters during extrusion and rolling. Compared with the traditional fixed parameter method, this method improves process stability and reduces the problem of uneven performance caused by parameter fluctuations during the preparation process.

[0153] (3) Adopt a closed-loop optimization mechanism to improve the intelligence and industrialization level of the production process This application constructs an intelligent optimization closed-loop control system based on mechanical property testing and EBSD microstructure analysis. It optimizes process parameters through iterative optimization of artificial intelligence models, realizing full-process optimization from data acquisition, intelligent analysis to production control, and effectively improving the production efficiency and performance stability of magnesium alloy thin plates.

[0154] The following are its main beneficial effects: (1) Through artificial intelligence optimization algorithms, accurate optimization of alloy composition and process parameters is achieved to improve the overall performance of the material. This application establishes a correlation model between alloy composition, microstructure, processing technology, and mechanical properties based on artificial intelligence optimization algorithms, and iteratively optimizes rare earth elements, heat treatment processes, and deformation process parameters with different ratios. Compared with the traditional parameter adjustment method that relies on experimental experience, it can accurately predict the optimal process solution. This method effectively improves the tensile strength, elongation, and superplasticity of magnesium alloy thin plates, ensuring the feasibility of the material's application in high-performance structural parts.

[0155] (2) Combining real-time sensor monitoring with data-driven optimization to achieve intelligent control of process parameters and improve production process stability. During the extrusion and rolling process, this application combines real-time temperature, strain rate, dynamic recrystallization ratio and other sensor data to intelligently adjust processing parameters, so that the production process no longer relies on a fixed process window, but is based on dynamic process parameter optimization to achieve precise control. Compared with traditional fixed temperature control and manual adjustment methods, this method can reduce process fluctuations, improve the uniformity of the microstructure of magnesium alloy sheets, and enhance superplastic processing performance.

[0156] (3) Construct a closed-loop optimization control system to achieve iterative process optimization and improve industrial production efficiency. This application constructs an artificial intelligence-based closed-loop optimization control system. The final mechanical property data is obtained through EBSD microstructure analysis, tensile testing, hardness testing, etc., and iterative adjustments are made in combination with the optimization model to form a new round of optimal processing technology solutions. Compared with the traditional method that relies on experience adjustment, this method can reduce experimental costs, shorten the R&D cycle, and improve the stability of the industrial production process, making the magnesium alloy thin plate preparation process have a higher level of automation and intelligence.

[0157] Example 2: Figure 5 The structural block diagram of a system for preparing a low-cost, high-strength, superplastic rare earth magnesium alloy sheet according to an embodiment of the present application is shown. Figure 5 As shown, the structure may include: Data acquisition module 10 is used to acquire data related to the production of rare earth magnesium alloy sheet materials from multiple data sources, including raw material composition data, heat treatment data, extrusion process data, rolling process data, and final mechanical property data. This module uses high-precision sensors and a database storage system to collect key parameters such as alloy composition ratio, solution temperature, extrusion temperature, rolling rate, dynamic recrystallization ratio, and grain size distribution in real time, ensuring the comprehensiveness and accuracy of the data.

[0158] The data processing and preprocessing module 20 performs preliminary processing on the collected rare earth magnesium alloy preparation process data, including data denoising, outlier detection, missing value filling, and data normalization to ensure data consistency and validity. The processed data is stored in an efficient database for subsequent optimization analysis and model training.

[0159] The process optimization calculation module 30 is used to calculate and optimize the alloy preparation process parameters based on the data provided by the data processing module. This module uses machine learning algorithms and physical models to analyze the impact of different alloy compositions, heat treatment conditions, and deformation parameters on material properties, and calculates the optimized process parameters, including: Solution optimization parameters (solution temperature, solution time, cooling rate); Extrusion process parameters (extrusion temperature, extrusion rate, strain rate); Rolling process parameters (rolling temperature, deformation, rolling rate); Final heat treatment optimization parameters (aging temperature, aging time, annealing treatment).

[0160] This module iteratively adjusts parameters through an intelligent optimization algorithm to ensure that the produced magnesium alloy thin sheets have low cost, high strength and excellent superplasticity.

[0161] The extrusion and rolling process monitoring module 40 is used to monitor key process parameters in real time during the extrusion and rolling process of rare earth magnesium alloy thin plates, and feed them back to the process optimization calculation module for adjustment. This module uses high-precision temperature sensors, strain measurement equipment and visual inspection systems to monitor: Temperature, pressure, extrusion rate, and strain rate during extrusion; The material deformation, rolling temperature, dynamic recrystallization ratio, and grain refinement during the rolling process.

[0162] The monitoring data can be fed back to the control system in real time for online adjustment to improve the stability and consistency of the magnesium alloy thin sheet preparation process.

[0163] The structure and performance analysis module 50 is used to analyze and characterize the microstructure and mechanical properties of the material after the rare earth magnesium alloy sheet is prepared. This module includes: Electron backscatter diffraction (EBSD) system: used to determine grain size data, texture distribution and dynamic recrystallization ratio; Tensile testing machine: used to measure mechanical properties such as tensile strength, yield strength, and elongation; Microhardness testing system: used to determine the hardness distribution of materials; Scanning electron microscopy (SEM): used to analyze the microstructural characteristics of magnesium alloys.

[0164] The analysis results will be stored in the database and used to further optimize process parameters and improve the overall performance of the material.

[0165] The AI ​​Process Optimization and Iterative Learning Module 60 combines microstructure and performance analysis data to optimize and iteratively learn process parameters using artificial intelligence (AI) algorithms. This module trains machine learning models based on experimental data to predict the final material properties under different process conditions. Using methods such as genetic algorithms (GA) or Bayesian optimization (BO), iteratively adjusts alloy composition, heat treatment, extrusion, and rolling process parameters to achieve optimal final product performance.

[0166] The optimization iterative process of this module includes: Obtain experimental data and historical process parameters; Predict the impact of different parameters on performance based on machine learning models; Optimize the objective function and automatically adjust the preceding process parameters; Generate a new round of optimized process plan and feed it back to the preparation system.

[0167] The user interaction and visualization module 70 is used to display process optimization results, material microstructure analysis data, and mechanical property test results through an intuitive user interface. This module supports: Real-time data display and trend analysis; 3D visualization of microstructure display; Simulation of material properties under different process parameters; Automatically generate optimization reports to guide the next step of process adjustment.

[0168] This module provides decision support for R&D personnel and production engineers, improving process optimization efficiency.

[0169] Beneficial effects of the embodiment: (1) Intelligently optimize process parameters and improve material properties. Through AI optimization calculation, process parameters such as solid solution, extrusion, rolling, and heat treatment are automatically adjusted to improve the tensile strength, elongation, and microstructure uniformity of the final plate.

[0170] (2) Real-time monitoring and feedback to improve the stability of the preparation process. Online sensors are used to monitor the temperature, strain rate, and dynamic recrystallization ratio during extrusion and rolling to ensure that the process parameters are in the optimal state and improve product consistency.

[0171] (3) Efficient data-driven optimization reduces experimental costs. By using machine learning models to predict material properties under different process conditions, the number of experiments can be reduced, the development of new materials can be accelerated, and the cost of production tests can be reduced.

[0172] (4) Accurately control the microstructure and improve superplasticity. Through EBSD analysis combined with AI optimization, grain refinement and microstructure uniformity control are achieved, and the superplasticity of magnesium alloy thin plates is improved, which is suitable for high-performance application scenarios such as aerospace and automotive lightweighting.

[0173] (5) Human-computer interaction and visualization improve process controllability. Through the visual interface, process data, tissue analysis results and mechanical property predictions are displayed in real time, which makes it easier for operators to adjust the process and improve the controllability of the preparation process.

[0174] In summary, the system provided in this application achieves low-cost, high-strength, and superplastic preparation of rare earth magnesium alloy thin plates through an intelligent, data-driven process optimization method, improves the comprehensive performance of the material, and promotes the industrial application of new magnesium alloy materials.

[0175] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. A method for preparing a low-cost, high-strength superplastic rare earth magnesium alloy thin plate, characterized in that: The method comprises: Obtain the composition data of the Mg-RE-Zn-Zr alloy, calculate the optimal rare earth element ratio based on the artificial intelligence optimization algorithm, and generate the optimized alloy composition plan; Extracting key element ratios from the optimized alloy composition scheme, performing solution heat treatment, and obtaining microstructural parameters after solution treatment; Based on the microstructure parameters and combined with real-time sensor data, the temperature and strain rate during the extrusion process are intelligently adjusted to generate dynamic extrusion process parameters; Obtaining the dynamic extrusion process parameters, performing electron backscatter diffraction structure analysis on the extruded magnesium alloy sheet, generating microstructure refinement features, and extracting grain size data; Based on the grain size data and temperature feedback information, intelligently optimize a target strain rate rolling process to generate an optimal rolling deformation and temperature control curve, wherein the target strain rate rolling process involves a strain rate greater than a preset rate threshold; Obtain the temperature control curve and, in combination with the intelligent temperature control system, adjust the induction heating during the rolling process in real time to maintain the optimal processing temperature; Based on the optimal processing parameters, the mechanical properties data of the magnesium alloy sheet are obtained, and the previous process parameters are optimized and iterated in combination with the artificial intelligence (AI) model to generate a final optimization solution; The method is based on the following optimization objective function: in, Indicates rolling temperature; Indicates the deformation of a single pass; Indicates the rolling line speed; Indicates the average grain size data of magnesium alloy sheet after final rolling; represents the final dynamic recrystallization ratio; Indicates the optimized target temperature; 、 、 Represents the weight coefficient.

2. The preparation method according to claim 1, characterized in that The method of obtaining the composition data of the Mg-RE-Zn-Zr alloy, calculating the optimal rare earth element ratio based on an artificial intelligence optimization algorithm, and generating an optimized alloy composition scheme includes: Extract the experimental data of historically prepared Mg-RE-Zn-Zr alloys, including the ratio information of Gd, Nd, Zn, Zr rare earth and trace elements, and form an alloy composition database; Analyzing the alloy composition database, calculating the effects of different ratios on mechanical properties, superplasticity, and cost based on the artificial intelligence optimization algorithm, generating the optimization objective function, and constructing an alloy composition optimization model; Based on the optimization objective function, the proportion of alloy elements is adjusted to generate an optimal alloy formula that meets the requirements of high strength and superplasticity, and the optimized alloy composition scheme is output.

3. The preparation method according to claim 1 or 2, characterized in that The step of extracting key element ratios from the optimized alloy composition scheme, performing solution heat treatment, and obtaining microstructure parameters after solution treatment includes: Extracting the key element ratios of the optimized alloy composition scheme, determining the solid solution temperature range of the rare earth elements Gd, Nd, Zn, and Zr, and generating solid solution treatment parameters; According to the solution treatment parameters, the Mg-RE-Zn-Zr alloy is subjected to a solution heat treatment in the range of 480° C. to 545° C. and maintained for 8 to 36 hours to obtain a uniform solution structure; The phase distribution after solid solution is detected by scanning electron microscopy (SEM) and energy dispersive spectroscopy (EDS), and the microstructure parameter data after solid solution is generated and transferred to the extrusion process module.

4. The preparation method according to claim 3, characterized in that Based on the microstructure parameters and combined with real-time sensor data, the temperature and strain rate in the extrusion process are intelligently adjusted to generate dynamic extrusion process parameters, including: Obtaining the microstructure parameters after the solid solution, combining the real-time temperature, stress, and strain sensor data, and processing the heating temperature of the extrusion process, the mold preheating state, and the extrusion speed; Optimizing the extrusion process parameters, calculating the optimal extrusion temperature range and the optimal extrusion rate based on finite element simulation (FEM), and generating the dynamic extrusion process parameters; Based on the dynamic extrusion process parameters, the extrusion process is adjusted, and precise temperature control and rate regulation are performed using an induction heating system and a real-time strain monitoring device to obtain a magnesium alloy thin plate with uniform structure.

5. The preparation method according to claim 1, characterized in that The obtaining of the dynamic extrusion process parameters, performing electron backscatter diffraction structure analysis on the extruded magnesium alloy sheet, generating microstructure refinement features, and extracting grain size data, includes: Obtain the microstructure data of the extruded magnesium alloy sheet, scan the sample using an EBSD analysis system, and obtain grain size data and orientation distribution microstructure data; Analyzing the organizational data, calculating average grain size data and dynamic recrystallization ratio after extrusion, and generating the microstructural refinement characteristics; The grain size data is extracted, the superplasticity trend is analyzed based on the microstructure refinement characteristics, and the trend data is transmitted to a high strain rate rolling optimization module to guide the setting of rolling process parameters.

6. The preparation method according to claim 5, characterized in that The target strain rate rolling process is intelligently optimized based on the grain size data and temperature feedback information to generate an optimal rolling deformation and temperature control curve, including: Acquire the grain size data and the temperature feedback information, form a material property database before rolling based on the microstructure data analyzed by EBSD, and combine the roll temperature and deformation history data; Analyzing the material property database, calculating optimal high strain rate rolling parameters based on an artificial intelligence model, including single-pass deformation, optimal rolling temperature and linear speed, and generating the temperature control curve; Based on the temperature control curve, the rolling process is optimized, and the induction heating system of the rolling process is regulated so that the rolling deformation and temperature are controlled within the optimized range.

7. The preparation method according to claim 1, characterized in that The obtaining of the temperature control curve and the combination of the intelligent temperature control system to adjust the induction heating in the rolling process in real time to maintain the optimal processing temperature include: Obtain the temperature control curve and real-time processing temperature data, collect the roll temperature and rolling temperature based on the intelligent temperature sensor, and perform matching analysis with the optimized temperature control curve; The rolling temperature is intelligently adjusted. When the actual processing temperature deviates from the optimized temperature control curve, the power output of the induction heating system is adjusted to maintain the processing temperature within the optimal range.

8. The preparation method according to claim 1, characterized in that The method of obtaining the mechanical property data of the magnesium alloy sheet based on the optimal processing parameters and optimizing the preceding process parameters iteratively in combination with the artificial intelligence model to generate a final optimization solution includes: Obtaining the optimal processing parameters and plate performance data, and extracting the tensile strength, elongation, and microhardness performance indicators of the final magnesium alloy plate based on tensile tests, hardness tests, and EBSD analysis methods; Based on artificial intelligence prediction models, the impact of processing parameters on final performance is analyzed, optimization targets are updated, and preceding process parameters are adjusted; Generate the final optimization plan, form the optimal process path for the preparation of rare earth magnesium alloy plates, and use it to guide the next round of production process optimization.

9. The preparation method according to claim 1, characterized in that The training process of the artificial intelligence model includes: Obtain historical process parameters and material properties data to construct a training dataset containing alloy composition, heat treatment parameters, deformation parameters, and final mechanical properties; Using an artificial intelligence optimization method based on a deep neural network (DNN) or a support vector regression (SVR) model to model the training data set and extract a mapping relationship between alloy composition and final mechanical properties; A genetic algorithm (GA) or a Bayesian optimization (BO) method is used to optimize the parameters of the artificial intelligence model to generate an artificial intelligence process optimization model for prediction and optimization.

10. The preparation method according to claim 1, characterized in that The final optimization solution is used for industrial production control, and the method further comprises: Generate process specification files containing optimized process parameters and store them in the database for industrial production line access; During the production process, process parameters are monitored in real time and dynamically adjusted based on the final optimization plan, including adjusting key process parameters such as alloy ratio, solution temperature, extrusion rate, rolling temperature and deformation amount; Through the intelligent control system, the temperature, pressure and deformation rate of the production equipment are automatically adjusted to match the optimized process path, and the feedback control mechanism is used to iteratively update the process optimization plan.

Images