High-throughput preparation and analysis method of metal material and metal piece

Abstract

The invention relates to the field of material preparation, and provides a high-throughput preparation and analysis method of a metal material and a metal piece, and the method comprises the following steps: selecting raw materials in a metal material formula, and weighing the raw materials according to the formula proportion of the metal material; putting the weighed raw materials into mixing equipment, and mixing by adopting a preset process, so that the raw material components are uniformly mixed; the mixed raw materials are added into high-throughput synthesis equipment, technological parameters are automatically matched through an AI optimization system according to the actual total weight of the raw materials, smelting, pouring and cooling are completed, and a metal material is formed; and component detection and mechanical property testing are carried out on the formed metal material, and test data are fed back to an AI optimization system so as to optimize subsequent batch process parameters. The process parameters can be automatically calculated according to the total weight of the raw materials; the preparation process can realize full-link accurate control and AI optimization, ensures performance consistency, is low in defect rate and high in purity, and reduces the production cost; the method is convenient for industrial replication and popularization and suitable for large-scale production.

Description

Technical Field

[0001] This invention relates to the field of materials preparation technology, and in particular to a high-throughput preparation and analysis method for metallic materials and a metallic component. Background Technology

[0002] In traditional metal alloy manufacturing processes, the control of alloy composition and properties largely relies on experience and static process parameter settings. Process parameters such as temperature, atmosphere, and pressure during alloy synthesis are typically set based on historical experience and theoretical models. However, due to the complexity of metal alloy production processes and the influence of numerous variables, traditional manual control methods often cannot flexibly respond to changes in various external factors, leading to unstable alloy properties and an inability to achieve efficient dynamic adjustment of the production process.

[0003] As the manufacturing industry increasingly demands efficient, stable, and high-quality production, traditional metal alloy manufacturing processes have revealed significant shortcomings. These shortcomings are mainly manifested in the following aspects: First, traditional processes lack in-depth analysis and immediate feedback mechanisms for real-time data during production; second, manual adjustment of synthesis parameters is often affected by human factors and technical limitations, making it difficult to ensure the stability and consistency of the synthesis process. Summary of the Invention

[0004] The present invention aims to solve at least one of the problems existing in the prior art by providing a high-throughput preparation and analysis method for metallic materials and a metallic component, so as to solve the problem that most of the existing technologies rely on manual or statically set process parameters and cannot analyze and adjust the synthesis conditions in real time.

[0005] One aspect of the present invention provides a high-throughput preparation and analysis method for metallic materials, comprising: Select the raw materials for the metal material formula and weigh them according to the formula ratio; The weighed raw materials are put into the mixing equipment and mixed using a preset process to ensure that the raw material components are evenly mixed. The mixed raw materials are added to a high-throughput synthesis equipment. The AI ​​optimization system automatically matches the process parameters according to the actual total weight of the raw materials to complete the melting, casting and cooling processes, so that the metal material is formed. The formed metal materials are subjected to compositional analysis and mechanical property testing. The test data is then fed back to the AI ​​optimization system to optimize the process parameters for subsequent batches.

[0006] Optionally, the metal material is 304 stainless steel, with a formula ratio of Cr: 18%-20%, Ni: 8%-10.5%, C: less than or equal to 0.08%, and the balance being Fe.

[0007] Optionally, the mixing equipment is a horizontal double-ribbon mixer; The raw materials are mixed using a pre-defined process to ensure uniform mixing, including: When the actual total weight of the raw materials is 5kg-10kg, set the mixing speed to 100r / min-200r / min and the mixing time to 10-20 minutes; when the actual total weight of the raw materials is 10kg-50kg, set the mixing speed to 200r / min-300r / min and the mixing time to 20-30 minutes. The raw materials are mixed according to the set mixing speed and mixing time. During the mixing process, the vibration device built into the mixing equipment is activated for 10 seconds every 5 minutes, and the vibration frequency is set to 50Hz. After the raw materials are mixed, the contents of Cr and Ni in the raw materials are detected by X-ray fluorescence spectrometry. When the test results show that the deviation of the contents of Cr and Ni is less than or equal to ±0.3%, the raw materials are judged to be qualified for mixing.

[0008] Optionally, the high-throughput synthesis equipment is a vacuum induction melting furnace; the parameters of the vacuum induction melting furnace include a rated power of 50kW-200kW and a vacuum degree of less than or equal to 5×10⁻⁶. -3 Pa, crucible capacity is 5kg-100kg; The smelting process adopts a stepped heating method, with the highest smelting temperature being 1600℃-1650℃; The pouring temperature during the pouring process is 1500℃-1550℃; The cooling process uses water cooling, with a cooling rate of 5℃ / min - 20℃ / min.

[0009] Optionally, the AI ​​optimization system includes a weight detection module, a parameter mapping module, and a real-time correction module; The weight detection module is a weighing module integrated into the furnace body of the high-throughput synthesis equipment, used to obtain the actual total weight of the raw materials; The parameter mapping module has a preset total weight-process parameter correlation model, and the process parameters include melting power, holding time, heating rate, and cooling water flow rate. The real-time correction module monitors the molten pool temperature using an infrared thermometer. When the deviation between the measured molten pool temperature and the predicted temperature of the AI ​​optimization system exceeds 30°C, the real-time correction module automatically fine-tunes the smelting power.

[0010] Optionally, the parameter adjustment rules of the total weight-process parameter correlation model include: For every 10kg increase in the actual total weight of the raw materials, the smelting power increases by 10kW-15kW, and the smelting power does not exceed the rated power of the vacuum induction melting furnace; For every 10kg increase in the actual total weight of the raw materials, the heat preservation time should be extended by 5-10 minutes. When the actual total weight of the raw materials is less than or equal to 10 kg, the heating rate is set to 50 °C / min. When the actual total weight of the raw materials is greater than 10 kg, the heating rate is set to 30 °C / min.

[0011] Optionally, the parameter adjustment rules of the total weight-process parameter correlation model include: During the cooling stage, for every 5kg increase in the actual total weight of the raw materials, the cooling water flow rate increases by 0.5L / min to 1L / min.

[0012] Optionally, the total weight-process parameter correlation model adopts a BP neural network model; the input parameters of the BP neural network model are the actual total weight of the raw materials, the initial room temperature, and the target melting temperature, and the output parameters are the melting power, the heating time, and the cooling rate.

[0013] Optionally, the raw materials include metal powder and nanoparticle reinforcing agents.

[0014] In another aspect, the present invention provides a metal part prepared according to the high-throughput preparation and analysis method for metal materials described above.

[0015] Compared with the prior art, the present invention has the following advantages: 1. The AI ​​optimization system, especially the total weight-process parameter correlation model in the AI ​​optimization system, can automatically calculate process parameters based on the actual total weight of raw materials, eliminating the need for repeated manual adjustments and solving the problems of low efficiency and error-proneness in traditional production that rely on experience to adjust parameters. At the same time, the BP neural network model combines the actual total weight of raw materials, initial room temperature, and target melting temperature to output corresponding process parameters, further improving the accuracy of parameter matching.

[0016] 2. Precise control and AI optimization of the entire preparation process can ensure the consistency of performance between the same batch and different batches, with low defect rate and high purity, eliminating the need for additional rework and reducing production costs; at the same time, the process of this invention is clear and the parameters are quantified, which is convenient for industrial replication and promotion and is suitable for large-scale production. Attached Figure Description

[0017] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0018] Figure 1A flowchart of a high-throughput preparation and analysis method for metallic materials provided in Embodiment 1 of the present invention; Figure 2 A schematic diagram of a high-throughput preparation and analysis method for metallic materials provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of a high-throughput preparation and analysis method for metallic materials provided in Embodiment 3 of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details are presented in the embodiments of the present invention to facilitate a better understanding of the invention. However, the technical solutions claimed in the present invention can be implemented even without these technical details and various variations and modifications based on the following embodiments. The division of the following embodiments is for ease of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with and referenced by each other without contradiction.

[0020] Example 1: Please see the appendix Figure 1 This embodiment provides a high-throughput preparation and analysis method for metallic materials, including the following steps: Step 1: First, prepare the basic metallic elements and nanoparticle reinforcing agents; Step 2: Mix the prepared metal powder and nanoparticles. Mix the metal powder and nanoparticle reinforcing agent according to a predetermined ratio to ensure that the particles are evenly dispersed. Step 3: Use high-throughput synthesis equipment to synthesize the mixed materials into a metal alloy; Step 4: During the synthesis process, temperature and atmosphere are controlled using temperature control and atmosphere control devices. Step 5: Use an AI optimization system to automatically control the alloying process and adjust the synthesis parameters in real time to control the quality and performance of each batch of alloy.

[0021] The basic metallic elements include aluminum (Al), titanium (Ti), zirconium (Zr), chromium (Cr), and nickel (Ni). The nanoparticles have a particle size of 10 nm to 100 nm and a predetermined ratio of 90% to 95% metal powder and 5% to 10% nanoparticle reinforcing agent, with the sum of the metal powder and nanoparticle reinforcing agent being 100%.

[0022] Nanoparticle reinforcing agents include nano-metal particles, carbon nanotubes, carbides, and nitrides.

[0023] The mixing of metal powder and nanoparticles can be achieved by ultrasonic treatment or sol-gel method, wherein the ultrasonic treatment power is 100W-1000W and the treatment time is 10 minutes-60 minutes.

[0024] Specifically, firstly, aluminum, titanium, zirconium, chromium, and nickel were selected as the base elements. These metallic elements possess excellent mechanical properties, good corrosion resistance, and high thermal stability, making them widely adaptable in alloy material applications. Unlike traditional metal alloys, this invention employs nanoparticle reinforcing agents to improve the overall performance of the metal alloy. These nanoparticle reinforcing agents include nano-metal particles, carbon nanotubes, carbides, and nitrides. These reinforcing agents exhibit excellent strength, hardness, and thermal conductivity. The addition of nanoparticles not only increases the grain boundary area of ​​the metal alloy but also enhances the strength of the metal matrix through the "particle reinforcement effect." At the nanoscale, the particle interface can significantly improve the deformation resistance of the metal matrix. By precisely controlling the ratio of metal powder to nanoparticles, the mechanical strength and corrosion resistance of the alloy are enhanced, while excessive aggregation of nanoparticles is avoided, ensuring their uniform distribution within the alloy.

[0025] The mixing of metal powder and nanoparticles is achieved using a combination of ultrasonic treatment and a sol-gel method. Ultrasonic treatment generates strong shear forces between the metal powder and the nanoparticle reinforcing agent through mechanical vibrations produced by high-frequency sound waves. This shear force breaks down particle aggregation, ensuring uniform dispersion of the nanoparticles. Ultrasonic treatment mixes the metal powder and nanoparticle reinforcing agent through the action of high-frequency sound waves. The localized high-temperature and high-pressure zones generated by the sound wave vibrations reduce the interfacial forces between particles, thereby achieving particle dispersion and strengthening. The mechanical effect of ultrasound not only prevents particle agglomeration but also increases the contact area between the particles and the metal matrix, enhancing the reinforcing effect of the reinforcing agent on the matrix. By controlling the ultrasonic power and time, the dispersibility of the nanoparticles and the controllability of the alloy are ensured, avoiding performance degradation caused by excessive particle aggregation.

[0026] High-throughput synthesis equipment includes mechanical alloying devices, laser melting devices, or hot static pressing devices. Mechanical alloying devices operate at speeds ranging from 300 rpm to 1000 rpm. Laser melting devices have power ranges from 1 kW to 10 kW and scanning speeds ranging from 5 mm / s to 20 mm / s.

[0027] Specifically, mechanical alloying involves repeatedly impacting and crushing metal powder during a high-energy ball milling process. The energy generated causes plastic deformation of the metal particles, leading to welding, fracture, and re-welding processes, thereby achieving the mixing and alloying of different metals. In this process, mechanical alloying can break the interatomic bonding forces between metal particles, allowing the metal to form a nanoscale structure during dispersion, thus improving the alloy's strength, hardness, and other mechanical properties. Furthermore, by rationally controlling the rotation speed, the microstructure of the alloy can be optimized, significantly improving its uniformity and stability.

[0028] Laser melting equipment uses a focused laser beam to create a high-temperature, high-energy zone on the material surface, causing localized melting and rapid solidification of metal powder. In this process, the laser's energy density controls the depth and width of the melting zone, thus determining the alloy's microstructure and final properties. Higher power helps improve melting efficiency, while a lower scanning speed ensures sufficient time for uniform melting and diffusion reactions. By rationally controlling power and scanning speed, rapid alloy forming can be achieved while maintaining quality, thereby improving the overall performance of the metal alloy, especially in high-performance structural materials. Hot static pressing (HSP) equipment applies static pressure and high temperature to promote welding between metal particles, eliminating voids in the powder and increasing the material's density. During this process, the interparticle adhesion is further enhanced, forming a uniform and dense alloy structure. Under high-temperature conditions, diffusion between particles is intensified, facilitating the fusion of different metals, resulting in excellent mechanical properties and a stable microstructure. The high temperature and high pressure of HSP provide an ideal processing environment for metal materials, significantly improving their strength, hardness, and corrosion resistance.

[0029] During the synthesis of the metal alloy, the temperature range was set to 300°C - 2000°C, the atmosphere flow rate was set to 1 ml / min - 1000 ml / min, and the atmosphere pressure was set to 1 MPa - 10 MPa.

[0030] Specifically, at lower temperatures, atomic diffusion of metal particles is slower, but still sufficient to promote intermetallic reactions. As temperature increases, interparticle diffusion accelerates, enhancing alloying reactions and grain refinement. Higher temperatures also promote rapid solidification and high-temperature reactions, helping alloys to form finer, more uniform microstructures. Lower gas flow rates result in slower gas turnover, maintaining the stability of the reaction system and helping to reduce the occurrence of oxidation or reduction reactions. Higher flow rates help improve the contact efficiency between the gas and metal powder, especially during high-temperature processing, where increased gas flow rates accelerate the melting and solidification of metal particles, thereby improving alloy formation efficiency and uniformity.

[0031] The control of atmosphere pressure has a significant impact on the densification and mechanical property improvement of metal alloys. The atmosphere pressure range of this invention is set from 1 MPa to 10 MPa to accommodate different alloy preparation requirements. At lower pressures, the sintering and melting process of metal powders is relatively slow, while at higher pressures, the contact force between metal particles is enhanced, which helps to accelerate the sintering process and improve the densification of the alloy. This is because higher atmosphere pressure promotes the sintering and bonding of metal powders by enhancing the contact force between particles, thereby improving the density and mechanical properties of the alloy. Simultaneously, increasing the atmosphere pressure can also affect the solubility of gases, promoting the diffusion and dissolution of alloying elements, and improving the uniformity and overall performance of the alloy.

[0032] The AI ​​optimization system, based on machine learning algorithms, analyzes data in the alloying process in real time, automatically adjusts synthesis parameters, and uses the adjusted synthesis parameters to optimize the metal alloy formula, as well as record the performance and quality of each batch of products.

[0033] Specifically, the AI ​​optimization system integrates sensors, data interfaces, and control execution units to collect core process parameters and environmental variables in real time during the alloying process, such as temperature profiles, reaction times, atmosphere flow rates, and the proportion of metal elements added. This real-time data collection not only provides a rich feature base for subsequent performance analysis, but more importantly, the AI ​​optimization system dynamically identifies and judges trends in the current process state by calling its built-in machine learning model simultaneously with the data flow. Unlike traditional process parameter control that relies on manual experience or static settings, the AI ​​optimization mechanism of this invention can automatically adjust the synthesis parameters immediately based on the results output by the machine learning model when a performance deviation trend is detected, ensuring that the process always converges towards the target performance range.

[0034] The real-time analysis and automatic adjustment mechanism of the AI ​​optimization system is one of the core technologies of this invention. Its innovative mechanism lies in: deeply modeling the multi-dimensional relationship between historical formulas, processes, and performance through machine learning models, enabling the machine learning model to "learn from experience" from existing production results. Unlike traditional static formula libraries, this machine learning model has dynamic evolutionary characteristics; each input of production data feeds back into the model, improving its predictive accuracy and adjustment sensitivity. This feedback optimization mechanism with learning capabilities allows the AI ​​optimization system not only to maintain product performance stability but also to automatically make adaptive adjustments under different production batches, different raw material sources, or changes in the external environment, significantly improving the reliability and robustness of metal alloy manufacturing under complex working conditions.

[0035] Furthermore, this invention establishes an accompanying recording mechanism that automatically records the performance testing data and final quality evaluation results of each batch of alloy products while adjusting synthesis parameters. This recording goes beyond simply storing results data; more importantly, it achieves an organic link between parameters, performance, and quality, forming a traceable, verifiable, and optimizable knowledge loop. This mechanism enables each batch of production activities to accumulate experience for subsequent production and, when necessary, allows for process traceability and quality responsibility determination, overcoming the technical bottlenecks of "data fragmentation" and "knowledge fragmentation" in traditional production systems.

[0036] Example 2: Please see the appendix Figure 2 This embodiment provides a high-throughput preparation and analysis method for metallic materials, including the following steps: Step 1: Use a high-throughput performance testing platform to perform performance testing on the metal alloy; Step 2: Upload the performance test data to the AI ​​analysis platform, and use data analysis methods to evaluate the comprehensive performance of the alloy and identify the relationship between metal composition and performance. Step 3: Use an AI platform to perform multi-dimensional analysis of the different properties of the alloy material and identify the correlation between each property and the composition of the metal alloy. Step 4: Based on the AI ​​analysis results, automatically optimize the formulation, production process, and synthesis conditions of the metal alloy; Step 5: By analyzing and identifying the correlation between various properties and the composition of the metal alloy, a real-time feedback mechanism is formed. Each test and production data is fed back to the AI ​​analysis platform. The platform automatically adjusts the alloy composition, microstructure, and synthesis conditions based on the data to control the consistency of each product generated.

[0037] The performance testing of metal alloys includes hardness, tensile strength, corrosion resistance, wear resistance, and thermal conductivity. Different performance evaluations are conducted using instruments such as a Vickers hardness tester, electronic universal testing machine, salt spray chamber, and laser flash method. The testing cycle ranges from 24 hours to 1000 hours, and the testing temperature range is 35°C to 50°C. Hardness testing uses a Vickers hardness tester, tensile strength testing uses an electronic universal testing machine, corrosion resistance is tested using a salt spray chamber, and thermal conductivity is tested using the laser flash method.

[0038] Specifically, hardness testing is performed using a Vickers hardness tester. The Vickers hardness tester provides accurate hardness measurements by applying a fixed load to indent the metal surface and measuring the hardness value. Hardness testing is a fundamental method for evaluating the wear resistance, compressive strength, and resistance to plastic deformation of metal alloys, reflecting the alloy material's ability to withstand external forces during actual use.

[0039] Tensile strength testing is performed using an electronic universal testing machine. This machine accurately measures the maximum stress a metallic alloy can withstand during tension, thereby assessing its tensile strength and ductility. By simulating the stress conditions of a metallic alloy under actual working conditions, tensile strength testing reveals the material's fracture behavior and strength characteristics during tension, ensuring that the alloy possesses sufficient strength to meet application requirements.

[0040] Corrosion resistance testing utilizes a salt spray chamber. Salt spray testing simulates the corrosion of metallic materials in a salt spray environment, evaluating the corrosion resistance of alloys. In this test, metal alloy samples are exposed to a salt spray environment. The salt spray chamber accelerates the corrosion process by controlling temperature and humidity conditions, with test cycles typically ranging from 24 to 1000 hours. By evaluating the corrosion rate and degree of corrosion of the metal alloy samples, the durability of the alloy under harsh environments can be accurately assessed.

[0041] Wear resistance testing assesses the durability of metal alloys under frictional environments. It typically involves simulating changes in surface wear under actual friction conditions to determine the wear resistance. Wear resistance testing helps determine whether a metal alloy is prone to wear during long-term use, thus affecting its service life.

[0042] Thermal conductivity testing utilizes the laser flash method. The laser flash method is an advanced technique for accurately determining the thermal conductivity of materials. It involves irradiating the sample surface with a short-pulse laser and measuring the temperature change of the reflected light to calculate the thermal conductivity. Thermal conductivity testing effectively evaluates the thermal conductivity of metallic alloys in high-temperature environments, ensuring their stable operation in applications with significant temperature variations.

[0043] The AI ​​analytics platform uses machine learning algorithms to analyze performance data in real time. Data analysis methods include regression analysis and cluster analysis. Combined with historical feedback data, it automatically adjusts the formulation and production process of metal alloys.

[0044] Specifically, firstly, data acquisition is the foundation for the operation of the AI ​​analysis platform. During the production process of metal alloys, various performance data (such as hardness, tensile strength, and corrosion resistance) and production data (such as metal composition, temperature, and pressure) are collected in real time and fed back to the AI ​​analysis platform. After collection, the AI ​​analysis platform removes noise and outliers through a data preprocessing stage to ensure data quality and reliability.

[0045] Next, the AI ​​analytics platform uses data analysis methods such as regression analysis and cluster analysis to perform real-time analysis of performance and production data. Regression analysis identifies and quantifies the quantitative relationship between alloy composition, production processes, and alloy performance. Through regression models, it can predict the impact of changes in a specific component ratio or production parameter on alloy performance and adjust formulations or process conditions based on the prediction results. Cluster analysis is used to discover potential patterns and groups within the data. Through cluster analysis, alloy samples with similar performance can be grouped based on historical data, identifying which formulation and production process combinations produce optimal alloy performance. Cluster analysis can understand the performance trends of alloys under different compositions and production conditions, thereby automatically adjusting production processes to achieve optimal performance in new production cycles.

[0046] Then, the AI ​​analysis platform combines historical feedback data with results from previous production processes to further improve the model's predictive accuracy. Historical data not only provides the AI ​​analysis platform with real-world examples of the relationship between composition and performance but also helps it learn the long-term impact of different processes and conditions on the properties of metal alloys. In this way, the AI ​​analysis platform can optimize formulations and process parameters based on real-time data feedback and historical experience, ensuring consistency in quality and performance for each batch of metal alloys.

[0047] Finally, the AI ​​analysis platform automatically adjusts the metal alloy formulation and production process based on real-time analysis results. This adjustment can be an optimization of a specific alloy composition or a correction of production conditions (such as temperature and atmosphere flow rate). The AI ​​analysis platform can not only fine-tune when data deviations occur, but also perform large-scale optimizations at the end of each production cycle based on the latest performance data and historical data to continuously improve product quality.

[0048] Performance analysis includes the evaluation of multiple performance dimensions of metal alloys, such as corrosion resistance, thermal conductivity, fatigue resistance, and high temperature resistance. During the test, the evaluation time and temperature range for each performance can be adjusted.

[0049] The AI ​​analysis platform is used to automatically provide performance optimization solutions based on test data and provide real-time feedback to the production process to optimize alloy formulation, microstructure and production process.

[0050] Specifically, by comprehensively evaluating the metal alloy across multiple performance dimensions, an AI analysis platform is used to analyze test data in real time, thereby optimizing the alloy's formulation, microstructure, and production process. Specifically, performance analysis covers key properties such as corrosion resistance, thermal conductivity, fatigue resistance, and high-temperature resistance. By adjusting test time and temperature range, a comprehensive evaluation of each performance under different operating conditions is ensured. Based on this performance data, the AI ​​analysis platform automatically provides performance optimization solutions and feeds them back into the production process in real time, achieving automated optimization of the alloy production process.

[0051] During performance testing, the AI ​​analysis platform receives various performance data in real time and establishes a mapping relationship between the composition and performance of metal alloys through regression analysis and cluster analysis. The AI ​​analysis platform can identify which components and microstructures have a significant impact on the corrosion resistance, thermal conductivity, and fatigue resistance of metal alloys. For example, regression analysis can quantify the effect of a certain metallic element on improving the thermal conductivity of a metal alloy, or cluster analysis can identify the optimal performance of a specific alloy formulation in terms of fatigue resistance.

[0052] Based on real-time analysis results, the AI ​​analysis platform automatically generates performance optimization plans. These plans may include adjusting the formulation, microstructure, or manufacturing process of metal alloys. For example, if a metal alloy is found to have insufficient oxidation resistance at high temperatures, the AI ​​analysis platform may suggest increasing the proportion of a certain metal element or adjusting the synthesis temperature and atmosphere conditions to optimize its high-temperature resistance. Similarly, the AI ​​analysis platform can also adjust the grain structure of metal alloys based on fatigue test results to improve their fatigue resistance. The AI ​​analysis platform can provide real-time feedback of performance optimization plans to the production line and automatically adjust various parameters during the production process. This feedback mechanism is achieved through an automatic adjustment module integrated into the production system, ensuring that the composition, microstructure, and process conditions of the metal alloy match the optimization plan in real time. For example, the AI ​​analysis platform automatically adjusts the composition ratio of the metal alloy or adjusts the sintering temperature and time based on test data. This real-time optimization and adjustment ensures that the production process maintains optimal performance indicators throughout uninterrupted production, optimizing not only through real-time data but also by combining historical data to improve its predictive capabilities. Historical data provides the AI ​​analysis platform with performance under different conditions during past production processes, helping it to better adjust current production processes.

[0053] By using an AI analysis platform for automated analysis and optimization of metal alloy properties, stability and consistency in the alloy production process are ensured. The AI ​​analysis platform combines performance test data with regression and cluster analysis to intelligently generate optimization solutions, which are then fed back to the production process in real time. Through continuous optimization of the alloy's formulation, microstructure, and production process, this invention effectively improves the overall performance of metal alloys, meeting the needs of different industrial applications and ensuring high quality and consistency in each batch.

[0054] Using the high-throughput preparation and analysis method for metallic materials provided in this embodiment, a metallic part, including 304 stainless steel, can be prepared.

[0055] Example 3: Please see the appendix Figure 3 This embodiment provides a high-throughput preparation and analysis method for metallic materials, including the following steps: S1. Raw material preparation: Select the raw materials in the metal material formula and weigh them according to the formula ratio of the metal material. S2. Raw material mixing: The weighed raw materials are put into the mixing equipment and mixed using the preset process to make the raw material components uniformly mixed. S3. Melting and processing: The mixed raw materials are added to the high-throughput synthesis equipment. The AI ​​optimization system automatically matches the process parameters according to the actual total weight of the raw materials to complete the melting, casting and cooling processes, so that the metal material is formed. S4. Performance Analysis: Perform composition analysis and mechanical property testing on the formed metal materials, and feed the test data back to the AI ​​optimization system to optimize the process parameters for subsequent batches.

[0056] The metal material is 304 stainless steel; the formula ratio is Cr: 18%-20%, Ni: 8%-10.5%, C: less than or equal to 0.08%, and the balance is Fe. The actual total weight of the raw materials ranges from 5kg to 50kg.

[0057] The mixing equipment is a horizontal double-ribbon mixer. A preset process is used to mix the raw materials uniformly, including: setting the mixing speed to 100-200 r / min and the mixing time to 10-20 minutes when the total weight of the raw materials is 5kg-10kg; setting the mixing speed to 200-300 r / min and the mixing time to 20-30 minutes when the total weight of the raw materials is 10kg-50kg. The raw materials are mixed according to the set mixing speed and time. During the mixing process, the vibration device built into the mixing equipment is activated for 10 seconds every 5 minutes, with a vibration frequency set to 50Hz. After the raw materials are mixed, the Cr and Ni content in the raw materials is detected using an X-ray fluorescence spectrometer. When the detection results show that the deviation of the Cr and Ni content is less than or equal to ±0.3%, the raw material mixing is deemed qualified.

[0058] The high-throughput synthesis equipment is a vacuum induction melting furnace. The core parameters of the vacuum induction melting furnace include a rated power of 50kW-200kW and a vacuum degree of less than or equal to 5×10⁻⁶. -3 Pa; crucible capacity: 5 kg - 100 kg. The melting process employs a stepped heating method, with a maximum melting temperature of 1600℃-1650℃. The casting temperature is 1500℃-1550℃. The cooling process uses water cooling at a rate of 5℃ / min - 20℃ / min.

[0059] The AI ​​optimization system comprises a weight detection module, a parameter mapping module, and a real-time correction module. The weight detection module, integrated into the furnace body of the high-throughput synthesis equipment, has a weighing accuracy of ±0.1 kg and is used to obtain the actual total weight of the raw materials. The parameter mapping module has a preset total weight-process parameter correlation model, including melting power, holding time, heating rate, and cooling water flow rate. The real-time correction module monitors the molten pool temperature using an infrared thermometer with an accuracy of ±5℃. When the deviation between the measured molten pool temperature and the predicted temperature of the AI ​​optimization system exceeds 30℃, the real-time correction module automatically fine-tunes the melting power.

[0060] The parameter adjustment rules for the total weight-process parameter correlation model include: for every 10kg increase in the actual total weight of the raw materials, the melting power is increased by 10kW-15kW, and the melting power does not exceed the rated power of the vacuum induction melting furnace; for every 10kg increase in the actual total weight of the raw materials, the holding time is extended by 5-10 minutes; when the actual total weight of the raw materials is less than or equal to 10kg, the heating rate is set to 50℃ / min; when the actual total weight of the raw materials is greater than 10kg, the heating rate is set to 30℃ / min; during the cooling stage, for every 5kg increase in the actual total weight of the raw materials, the cooling water flow rate is increased by 0.5 L / min-1L / min.

[0061] The total weight-process parameter correlation model employs a backpropagation (BP) neural network. The input parameters of the BP neural network model are the actual total weight of the raw materials, the initial room temperature, and the target melting temperature. The output parameters are the melting power, heating time, and cooling rate. The BP neural network model has been trained with over 100 batches of 304 stainless steel smelting data, and the parameter prediction error is less than or equal to 5%.

[0062] Specific methods for performance analysis of formed metal materials include: using a direct-reading spectrometer for component detection; taking three samples each from the gating point, middle section, and bottom of the formed metal material for testing; using an electronic universal testing machine to test the mechanical properties of the formed metal material, including tensile strength and elongation; using a Vickers hardness tester to test the hardness of the formed metal material; and using a salt spray test chamber to test the corrosion resistance of the formed metal material through a neutral salt spray test.

[0063] The acceptable thresholds for performance analysis include: in component testing, the deviation of Cr content is less than or equal to ±0.5%, and the deviation of Ni content is less than or equal to ±0.5%; in mechanical properties, the tensile strength is greater than or equal to 515 MPa, the elongation is greater than or equal to 40%, and the hardness is less than or equal to 201 HV; in corrosion resistance testing, the salt spray test uses a 5% NaCl solution, the test temperature is set to 35℃, the test time is set to 48 hours, and the corrosion rate is set to less than or equal to 0.01 mm / year.

[0064] The AI ​​optimization system establishes a weight-performance feedback mechanism: when the tensile strength of a batch of metal materials is lower than 515 MPa, the AI ​​optimization system automatically extends the holding time by 3-5 minutes based on the actual total weight of the corresponding raw materials; when the corrosion rate of a batch of metal materials in the corrosion resistance test is greater than 0.01 mm / year, the AI ​​optimization system increases the vacuum degree of the vacuum induction melting furnace to less than or equal to 3 × 10⁻⁶ for the next melting of the same weight of raw materials. -3 Pa; Through a feedback mechanism, ensure that the pass rate of metal materials is greater than or equal to 98% under the actual total weight of different raw materials.

[0065] Example 4: Taking 304 stainless steel as an example, in a smelting scenario, the AI ​​optimization system automatically matches process parameters based on the actual total weight of the raw materials. The specific steps are as follows: Step 1: Accurate detection and data input of the actual total weight of the raw materials.

[0066] 1. Weight detection: Before the raw materials are put into the vacuum induction melting furnace, the actual total weight of the current batch of raw materials is collected in real time by a high-precision weighing sensor integrated into the furnace body. The preset effective range of total weight is 5kg-50kg. For example, the actual total weight of the raw materials detected is 25.3kg.

[0067] 2. Data Verification: The AI ​​optimization system automatically determines whether the actual total weight of the detected raw materials is within the preset total weight effective range of 5kg-50kg. If the actual total weight of the detected raw materials exceeds this effective range, an alarm is immediately triggered and the process is paused; if the actual total weight of the detected raw materials is within this effective range, the weight data is synchronized to the parameter calculation module.

[0068] 3. Auxiliary Data Acquisition: While collecting weight data, ambient temperature and initial furnace temperature are also collected as auxiliary parameters. These auxiliary parameters will be used as supplementary inputs for subsequent model calculations. The ambient temperature is defined as the workshop room temperature of 20℃-30℃.

[0069] Step 2: Total weight - process parameter association model call and initial parameter calculation.

[0070] The AI ​​optimization system calls a pre-trained BP neural network model as the total weight-process parameter correlation model, and calculates the initial process parameters based on the actual total weight of the raw materials. The actual total weight of the raw materials determines the energy input, holding time, and cooling efficiency. 1. The inputs to the total weight-process parameter correlation model include: the actual total weight of the raw materials (25.3 kg), the ambient temperature (25℃), and the initial furnace temperature (30℃, cold furnace state).

[0071] 2. Parameter calculation: Melting power: According to the weight-power positive correlation model, for every 10kg increase in the actual total weight of the raw materials, the melting power increases by 12kW, with a base power of 80kW corresponding to 5kg of weight. For example, 25.3kg corresponds to a melting power of 80+(25.3-5) / 10×12≈104.4kW, rounded to 105kW, and not exceeding the rated power of the vacuum induction melting furnace of 200kW.

[0072] Insulation time: Based on the weight-insulation time mapping table, 5kg-10kg corresponds to 30 minutes, 10kg-20kg corresponds to 40 minutes, 20kg-30kg corresponds to 50 minutes, and 30kg-50kg corresponds to 60 minutes. 25.3kg falls into the 20kg-30kg range, so the initial insulation time is set to 50 minutes.

[0073] Heating rate: 50℃ / min when the actual total weight of the raw material is less than or equal to 10kg, and 30℃ / min when the actual total weight of the raw material is greater than 10kg. Therefore, 25.3kg corresponds to 30℃ / min.

[0074] Cooling water flow rate: Calculated based on a flow rate of 1L / min for every 5kg of weight, 25.3kg corresponds to 5L / min, the basic flow rate is 2L / min, and the cooling water flow rate increases by 1L / min for every 5kg increase in the actual total weight of the raw material.

[0075] Step 3: Dynamic adaptation and output of process parameters.

[0076] The AI ​​optimization system, taking into account the characteristics of stainless steel smelting, performs a secondary adaptation of the initial parameters to ensure their rationality. 1. Power step adjustment: In order to avoid furnace temperature fluctuations caused by sudden changes in melting power, the 105kW power is divided into: 30kW for 5 minutes in the preheating stage; 105kW for the heating stage, which continues until 1600℃; and 90kW for 50 minutes in the holding stage, with step-wise output.

[0077] 2. Critical value verification: Check whether the parameters meet the equipment safety thresholds, the melting power is less than or equal to 200kW and the cooling water flow rate is less than or equal to 10L / min. If they exceed the thresholds, they will be automatically corrected. In one embodiment, the cooling water flow rate is calculated as 10L / min when the weight is 50kg, and it will not be increased after reaching the upper limit.

[0078] 3. Parameter output: The final parameters, such as power curve, holding time, and flow rate, are converted into executable instructions for the equipment and sent to the control cabinet of the vacuum induction melting furnace through the PLC control system, driving the equipment to operate according to the set parameters.

[0079] Step 4: Real-time monitoring and parameter correction of the smelting process.

[0080] During the smelting process, the AI ​​optimization system dynamically fine-tunes parameters through real-time data feedback to compensate for weight detection errors or environmental interference. 1. Key Indicator Monitoring: An infrared thermometer is used to monitor the molten pool temperature in real time, collecting data every 10 seconds; a vacuum gauge is used to monitor the vacuum level inside the furnace to ensure a stable smelting environment, with a target vacuum level of less than or equal to 5 × 10⁻⁶. -3 Pa.

[0081] 2. Deviation Judgment and Adjustment: If the measured temperature of the molten pool is more than 30°C lower than the temperature prediction value output by the model (e.g., if the temperature prediction value is 1500°C and the measured temperature of the molten pool is 1460°C, the measured temperature of the molten pool is 40°C lower than the temperature prediction value), the AI ​​optimization system will automatically increase the current melting power by 5kW and shorten the subsequent heating time to 2 minutes; if the vacuum fluctuation exceeds 1×10 -3 The AI ​​optimization system will automatically adjust the vacuum pump power to maintain environmental stability and avoid affecting the uniformity of alloy composition.

[0082] Step 5: Post-smelting performance feedback and model iteration.

[0083] After each batch of smelting is completed, the accuracy of subsequent parameter matching is improved by using a closed-loop optimization model based on performance data. 1. Performance data collection: The content of Cr and Ni in metallic alloys is determined by direct-reading spectrometer, and must meet the 304 standard, which specifies that Cr accounts for 18-20% and Ni accounts for 8-10.5%. Test indicators such as tensile strength (≥515MPa) and salt spray corrosion rate (≤0.01mm / year).

[0084] 2. Deviation Analysis: If the tensile strength of a batch of 25kg raw material is 500MPa, the AI ​​optimization system traces the historical parameters and judges that the heat preservation time is insufficient. It automatically adjusts the heat preservation time benchmark for the 20kg-30kg range from 50 minutes to 52 minutes.

[0085] 3. Model Update: Every day, the algorithm incorporates 5-10 batches of weight, parameter, and performance data into the training set to update the weight parameters of the BP neural network model, gradually reducing the parameter prediction error from the initial 5% to within 3%.

[0086] Through the five steps in this embodiment, the AI ​​optimization system can accurately map the actual total weight of raw materials, process parameters, and product quality. Even if the actual total weight of raw materials varies within the range of 5kg-50kg, the system can ensure the performance consistency of each batch of 304 stainless steel through dynamic parameter matching.

[0087] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

Claims

1. A method of high-throughput preparation and analysis of metallic materials, characterized in that, The application relates to a metal material production method and device. Selecting raw materials in a metal material formula, weighing the raw materials according to the formula proportion of the metal material; The weighed raw materials are put into a mixing device, and preset process is adopted to mix the raw materials so that the raw material components are uniformly mixed; The mixed raw materials are added into a high-throughput synthesis device, and an AI optimization system automatically matches process parameters according to the actual total weight of the raw materials, so that a melting process, a pouring process and a cooling process are completed, and the metal material is formed; The formed metal material is subjected to component detection and mechanical property testing, and the test data are fed back to the AI optimization system to optimize subsequent batch process parameters.

2. The method of high-throughput production and analysis of metallic materials according to claim 1, characterized in that, The metal material is 304 stainless steel, and the formula proportion is as follows: Cr: 18%-20%, Ni: 8%-10.5%, C: less than or equal to 0.08%, and the balance is Fe.

3. The method for high-throughput production and analysis of metallic materials according to claim 2, characterized in that, The mixing device is a horizontal double-screw ribbon mixer; The preset process is adopted to mix the raw materials so that the raw material components are uniformly mixed, which comprises the following steps: When the actual total weight of the raw materials is 5kg-10kg, the mixing rotation speed is set to 100r / min-200r / min, and the mixing time is 10min-20min; when the actual total weight of the raw materials is 10kg-50kg, the mixing rotation speed is set to 200r / min-300r / min, and the mixing time is 20min-30min; The raw materials are mixed according to the set mixing rotation speed and mixing time, and every 5min, the vibration device of the mixing device is started for 10s, and the vibration frequency is set to 50Hz during the raw material mixing process; After the raw material mixing is completed, the X-ray fluorescence spectrometer is adopted to detect the contents of Cr and Ni in the raw materials, and when the detection result shows that the content deviation of Cr and Ni is less than or equal to + / -0.3%, the raw material mixing is determined to be qualified.

4. The method of high-throughput production and analysis of metallic materials according to claim 1, characterized in that, The high-flux synthesis equipment is a vacuum induction melting furnace; parameters of the vacuum induction melting furnace include rated power of 50 kW -200 kW, vacuum degree of less than or equal to 5*10 -3 Pa, crucible capacity of 5 kg -100 kg; The melting process adopts stepwise temperature rising, and the highest melting temperature is 1600-1650 DEG C; The pouring temperature of the pouring process is 1500-1550 DEG C; The cooling process adopts water cooling, and the cooling rate is 5-20 DEG C / min.

5. The method of high-throughput production and analysis of metallic materials according to claim 1, wherein, The AI optimization system comprises a weight detection module, a parameter mapping module and a real-time correction module; The weight detection module is a weighing module integrated in the furnace body of the high-throughput synthesis device, and is used for acquiring the actual total weight of the raw materials; The parameter mapping module is provided with a total weight-process parameter correlation model, and the process parameters include melting power, holding time, temperature rising rate and cooling water flow rate; The real-time correction module monitors the molten pool temperature through an infrared temperature detector, and when the deviation between the actual molten pool temperature and the predicted temperature of the AI optimization system is greater than 30 DEG C, the real-time correction module automatically fine tunes the melting power.

6. The method for high-throughput production and analysis of metallic materials according to claim 5, characterized in that, The parameter adjustment rule of the total weight-process parameter correlation model comprises the following steps: When the actual total weight of the raw materials increases by 10kg, the melting power is increased by 10-15kW, and the melting power does not exceed the rated power of the vacuum induction melting furnace; When the actual total weight of the raw materials increases by 10kg, the holding time is prolonged by 5-10min; When the actual total weight of the raw materials is less than or equal to 10kg, the temperature rising rate is set to 50 DEG C / min; When the actual total weight of the raw materials is greater than 10kg, the temperature rising rate is set to 30 DEG C / min.

7. The method of high-throughput production and analysis of metallic materials according to claim 5, characterized in that, The parameter adjustment rule of the total weight-process parameter correlation model comprises: In the cooling stage, the cooling water flow rate is increased by 0.5L / min-1L / min for each increase of 5kg in the actual total weight of the raw material.

8. The method of high-throughput production and analysis of metallic materials according to claim 5, characterized in that, The total weight-process parameter correlation model adopts a BP neural network model; input parameters of the BP neural network model are the actual total weight of the raw material, the initial room temperature and the target smelting temperature, and output parameters are the smelting power, the temperature rising time and the cooling rate.

9. The method of high-throughput production and analysis of metallic materials according to claim 1, wherein, The raw material comprises metal powder and a nano-particle reinforcing agent.

10. A metal piece, characterized by, The metal part is prepared according to the high-throughput preparation and analysis method of the metal material in any one of claims 1 to 9.

Images