Self-antifouling nanocomposite conductive ceramic electrode and antifouling deposition method thereof

Abstract

The application provides a self-anti-fouling nano-composite conductive ceramic electrode anti-fouling deposition method, comprising: for an alloyed electrode base sample, carrying out a pressurization experiment in a high-pressure container to obtain the change rule of the compressive strength and the yield strength with the pressure, judging whether the sample meets the high-pressure resistance requirement according to the maximum pressure under the actual use condition; for the alloyed electrode base sample, carrying out a soaking corrosion experiment and an electrochemical impedance spectrum test, determining whether the alloying improves the corrosion resistance of the material by comparison with a pure base material, and obtaining the maximum use time in different corrosion media; establishing a whole-process database of the alloyed electrode base from preparation, characterization to use, using big data analysis and machine learning algorithms to mine the internal relationship between the preparation process, the organizational structure and the use performance, and optimizing the material composition and the process parameters according to the analysis result to realize the simultaneous improvement of the toughness and the conductive performance of the electrode base.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, and in particular to a scale deposition prevention method for a self-scale-prevention nano-composite conductive ceramic electrode. BACKGROUND

[0002] Under the harsh environment of high temperature, high pressure and strong corrosion, how to develop a self-scale-prevention nano-composite conductive ceramic electrode matrix material with excellent toughness and conductivity is a major challenge in the electrode manufacturing field. Traditional electrode matrix materials are prone to brittle fracture or reduced conductivity under extreme conditions, making it difficult to meet the requirements of long-term stable operation. Alloying modification can improve material toughness, but often reduces conductivity. How to find a balance between microstructure control and macroscopic performance to achieve the synergistic improvement of toughness and conductivity is a key problem that needs to be solved. At the same time, scale deposition easily occurs on the electrode during use, affecting its conductivity and service life. Therefore, how to construct a nano-composite coating with self-cleaning function on the surface of the electrode matrix to inhibit scale formation is also an important technical problem. In addition, the failure mechanism and life prediction model of the electrode matrix material under complex environment are not perfect, making it difficult to accurately evaluate its long-term performance. How to establish a quantitative relationship between material composition, preparation process, microstructure and performance to guide the optimization design of electrode matrix material is also a technical bottleneck that needs to be broken through. SUMMARY

[0003] The present application provides a scale deposition prevention method for a self-scale-prevention nano-composite conductive ceramic electrode, mainly comprising:

[0004] Obtain the composition ratio and process parameter data of the alloyed electrode matrix as the training sample set of the machine learning algorithm, and establish a nonlinear mapping relationship model between the composition-process-performance by using the support vector regression algorithm for the training sample set. According to the mapping relationship model, determine the optimal composition ratio and process parameter combination that takes into account toughness and conductivity;

[0005] Obtain the alloyed electrode matrix sample prepared by using the optimal composition ratio and process parameter combination, and obtain the microstructure parameters including grain size, precipitate distribution, and dislocation density by using an electron microscope and X-ray diffraction for the sample. Determine whether the microstructure parameters meet the preset range. If yes, it is determined that the alloying process obtains an ideal microstructure, and the preset range is determined according to the target performance requirements and material design experience;

[0006] For the alloyed electrode base sample with ideal microstructure, high temperature tensile test and high temperature creep test are used to characterize the high temperature toughness level, four-probe method is used to test the electrical conductivity, and whether the high temperature toughness level and the electrical conductivity meet the preset index is judged, if yes, it is determined that the alloyed electrode base can maintain stable comprehensive performance in high temperature environment, and the preset index includes that the yield strength at 600 DEG C is not less than 200 MPa, and the electrical conductivity is not less than 40 % IACS;

[0007] For the alloyed electrode base sample, pressure test is carried out in a high-pressure container, the change rule of the compressive strength and the yield strength with the pressure is obtained, and whether the sample meets the high-pressure resistance requirement is judged according to the maximum pressure under the actual use condition;

[0008] For the alloyed electrode base sample, immersion corrosion experiment and electrochemical impedance spectroscopy test are carried out, and whether the alloying improves the corrosion resistance of the material is determined by comparison with the pure base material, and the maximum use time in different corrosion media is obtained;

[0009] In the simulation use environment of high temperature, high pressure and strong corrosion, long-term working test is carried out on the alloyed electrode base sample, the microstructure evolution rule of the sample in the complex harsh environment is obtained, a quantitative relationship model of the microstructure parameters and the use time is established by using a machine learning algorithm, and the service life of the electrode base is predicted;

[0010] A full-process database of the alloyed electrode base from preparation, characterization to use is established, big data analysis and machine learning algorithm are used to mine the internal relationship between the preparation process, microstructure and use performance, and according to the analysis result, the material composition and process parameters are optimized, so that the toughness and electrical conductivity of the electrode base are improved.

[0011] The technical scheme provided by the embodiment of the application can include the following beneficial effects:

[0012] The application discloses a method for developing high-performance electrode base materials. The method obtains the composition and process data of the alloyed electrode base, establishes a composition-process-performance mapping model by using a machine learning algorithm, determines the optimal composition ratio and process parameters, and verifies whether the prepared sample meets preset indexes by performing microstructure and performance characterization. Long-term test is carried out in a simulated extreme environment, a quantitative model of microstructure evolution and use time is established, and the service life of the electrode is predicted. By establishing a full-process database and performing big data analysis, the internal relationship between the process, structure and performance is mined, and the toughness and electrical conductivity of the electrode base are improved. The application solves the problem that the electrode base material is prone to brittle fracture or electrical conductivity decline in a high-temperature, high-pressure and strong-corrosion environment, develops a self-antifouling nanocomposite conductive ceramic electrode base material with excellent toughness and electrical conductivity, and provides reliable protection for long-term stable work of the electrode. Attached Figure Description

[0013] Fig. 1 This is a flowchart of a method for preventing scale deposition in a self-scaling nanocomposite conductive ceramic electrode according to the present invention.

[0014] Fig. 2 This is a schematic diagram of a method for preventing scale deposition in a self-scaling nanocomposite conductive ceramic electrode according to the present invention.

[0015] Fig. 3 This is another schematic diagram of a method for preventing scale deposition in a self-scaling nanocomposite conductive ceramic electrode according to the present invention. Detailed Implementation

[0016] To further understand the content of this invention, a detailed description of the invention is provided in conjunction with the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0017] like Figs. 1-3 The anti-scaling deposition method for a self-scaling nanocomposite conductive ceramic electrode in this embodiment may specifically include:

[0018] Step S101: Obtain the composition ratio and process parameter data of the alloyed electrode matrix as a training sample set for the machine learning algorithm; for the training sample set, use the support vector regression algorithm to establish a nonlinear mapping relationship model between composition, process and performance; based on the mapping relationship model, determine the optimal composition ratio and process parameter combination that takes into account both toughness and conductivity.

[0019] The historical production data of the alloyed electrode base body is acquired, the historical production data includes component proportioning, process parameters and performance test results, the historical production data is taken as a training sample set of a machine learning algorithm; the training sample set is preprocessed, abnormal values are eliminated, numerical value type features are normalized, and a preprocessed training sample set is obtained; a support vector regression algorithm is adopted, the component proportioning and the process parameters in the preprocessed training sample set are taken as input features, and the toughness and the conductive performance are taken as output targets, and a nonlinear mapping relationship model of the performance of the alloyed electrode base body is established; a preset target value range of the toughness and the conductive performance is acquired, and the target value range is taken as a constraint condition for optimization of the nonlinear mapping relationship model; a grid search algorithm is adopted, an optimal component proportioning and process parameter combination is searched under the constraint condition, and a candidate optimal parameter combination is obtained; the candidate optimal parameter combination is input into the nonlinear mapping relationship model, the toughness and the conductive performance corresponding to the candidate optimal parameter combination are predicted, it is judged whether the predicted toughness and the predicted conductive performance satisfy the target value range, if yes, the candidate optimal parameter combination is determined as an optimal formula for production of the alloyed electrode base body, and if no, the grid search algorithm is executed again, and an optimal parameter combination is continuously searched.

[0020] Specifically, in the production process of alloyed electrode matrix, obtaining historical production data is the first crucial step. These data usually include ingredient proportions (such as the proportions of elements like copper, nickel, cobalt, etc.), process parameters (such as sintering temperature, pressing pressure, cooling rate, etc.), and performance test results (such as toughness, electrical conductivity, etc.). For example, the ingredient proportions of a certain batch of electrode matrix may be copper 70%, nickel 20%, and cobalt 10%, the process parameters are sintering temperature 900°C, pressing pressure 200 MPa, and cooling rate 10°C / min, and the performance test results show that the toughness is 120 MPa and the electrical conductivity is 98% IACS. Next, the historical production data is preprocessed. First, outliers are removed, such as test results that are significantly different from other data, which may be caused by equipment failure or operational errors. Second, numerical features are normalized to make data of different dimensions on the same scale, which facilitates subsequent machine learning algorithm processing. For example, the sintering temperature is normalized from 900°C to 0.9, and the pressing pressure is normalized from 200 MPa to 0.8. Using the support vector regression (SVR) algorithm, the preprocessed ingredient proportions and process parameters are used as input features, and the toughness and electrical conductivity are used as output targets to establish a non-linear mapping relationship model. SVR maps input features to high-dimensional space through kernel functions (such as radial basis function RBF), finds an optimal hyperplane that minimizes prediction error. For example, input features are [0.7, 0.2, 0.1, 0.9, 0.8, 0.1], and output targets are [120, 98], the model learns the complex relationship between these features and targets through training. Obtain the target value range of the predetermined toughness and electrical conductivity, such as the toughness requirement between 100-150 MPa and the electrical conductivity requirement between 95-100% IACS. These target value ranges are used as constraint conditions for model optimization to ensure that the final parameter combination meets the performance requirements. The grid search algorithm is used to search for the optimal ingredient proportions and process parameter combination under the constraint conditions. Grid search tries all possible parameter combinations to find the optimal solution. For example, set the search range of ingredient proportions to copper 60%-80%, nickel 10%-30%, and cobalt 5%-15%, and the search range of process parameters to sintering temperature 850°C-950°C, pressing pressure 150 MPa-250 MPa, and cooling rate 5°C / min-15°C / min. Grid search will try these combinations one by one to find the best parameters that meet the performance requirements. Input the candidate optimal parameter combination into the non-linear mapping relationship model to predict its corresponding toughness and electrical conductivity. For example, a candidate parameter combination is copper 75%, nickel 20%, and cobalt 5%, sintering temperature 900°C, pressing pressure 200 MPa, and cooling rate 10°C / min, the model predicts that the toughness is 130 MPa and the electrical conductivity is 97% IACS. Determine whether the predicted toughness and electrical conductivity meet the target value range. If they do, the parameter combination is determined as the optimal formula.For example, the above prediction results are all within the target range, so the combination is determined as the optimal formula. If not, return to execute the grid search algorithm to continue searching for the optimal parameter combination until a combination that meets the requirements is found. Through this method, the production formula of the alloyed electrode substrate can be systematically optimized, improving product quality and production efficiency. Preprocessing data ensures the accuracy of the model, the SVR model can capture complex nonlinear relationships, and the grid search ensures that the optimal solution is found under the constraints. The entire process is closely linked and logically rigorous, ultimately achieving the optimization of the production formula. This optimization method not only improves the performance of the alloyed electrode substrate, but also reduces production costs and enhances market competitiveness. Through data-driven methods, the inefficiency and high cost of traditional trial-and-error methods are avoided, making the production process more scientific and controllable. In addition, the model establishment and optimization process also provides valuable experience and reference for subsequent production, helping to continuously improve and enhance product quality. In practical applications, the model and search strategy can also be adjusted according to specific needs. For example, if the electrical performance requirement is higher, the weight of the electrical performance can be increased in the grid search, making the search process more inclined to find parameter combinations with better electrical performance. This flexibility and adjustability make the method adaptable to different production needs and environmental changes. In summary, by obtaining historical production data, data preprocessing, establishing an SVR model, setting constraints, searching for the optimal parameter combination through grid search, predicting performance and determining whether it meets the target value range, and finally determining the optimal production formula, this series of steps constitutes a complete and efficient production optimization process, providing strong technical support for the production of alloyed electrode substrates.

[0021] In step S102, an alloyed electrode substrate sample prepared using the optimal composition ratio and process parameter combination is obtained. For the sample, electron microscopy and X-ray diffraction are used to obtain microstructure parameters, including grain size, precipitate distribution, and dislocation density. It is determined whether the microstructure parameters meet the preset range. If yes, it is determined that the alloying process obtains the ideal microstructure, and the preset range is determined according to the target performance requirements and material design experience.

[0022] The ideal microstructure parameter range of the alloyed electrode substrate is obtained, including grain size, precipitate distribution, and dislocation density. The microstructure parameters of the alloyed electrode substrate sample are obtained, and the microstructure parameters are compared with the preset range. If the microstructure parameters meet the preset range, the optimized ratio and process parameters are determined to prepare the alloyed electrode substrate with ideal microstructure.

[0023] Specifically, obtaining the ideal microstructure parameter preset range of the alloyed electrode base is a key step to optimize the electrode performance. The ideal microstructure parameters usually include grain size, precipitate distribution, and dislocation density. These parameters directly affect the mechanical and electrical properties of the electrode. First, the grain size is an important factor affecting the mechanical properties of the material. Fine grains can improve the strength and toughness of the material, while larger grains may cause the material to become brittle. For example, the preset grain size range may be 10-30 microns to ensure that the electrode base has both sufficient strength and good toughness. Second, the precipitate distribution determines the uniformity and stability of the electrode base. Uniformly distributed precipitates can effectively improve the electrical conductivity and corrosion resistance of the material. For example, the preset precipitate distribution range may require precipitate particle diameters between 1-5 nanometers and uniform distribution. Finally, the dislocation density reflects the internal crystal defect situation of the material. Moderate dislocation density can improve the strength of the material, but excessive dislocation density may cause the material to become brittle. For example, the preset dislocation density range may be 10^6-10^8 / cm 2 In actual operation, the microstructure parameters of the alloyed electrode base sample are usually detected by scanning electron microscopy (SEM), transmission electron microscopy (TEM), and other technical means. For example, the grain size detection result of a batch of electrode base is 20 microns, the precipitate particle diameter is 3 nanometers and uniformly distributed, and the dislocation density is 5×10^7 / cm 2The microstructure parameters are compared with the preset range. If the preset range is met, the current composition ratio and process parameters can be determined as the optimal ratio. For example, if the detection results are all within the preset range, it indicates that the composition ratio (e.g., copper 70%, nickel 20%, and cobalt 10%) and process parameters (e.g., sintering temperature 900°C, pressing pressure 200MPa, and cooling rate 10°C / min) of this batch are ideal and can be used to prepare an alloyed electrode substrate with ideal microstructure. If the microstructure parameters do not meet the preset range, the composition ratio and process parameters need to be adjusted. For example, if the grain size is too large (e.g., 40 microns), the sintering temperature may need to be reduced or the pressing pressure may need to be increased to refine the grain size. If the precipitate phase distribution is uneven, the cooling rate may need to be adjusted to promote the uniform distribution of the precipitate phase. If the dislocation density is too high, the composition ratio may need to be optimized to reduce crystal defects. Through this method, the microstructure of the alloyed electrode substrate can be systematically optimized, thereby improving its overall performance. The realization of the ideal microstructure not only depends on accurate composition ratio and process parameters, but also requires precise control and optimization of microstructure parameters. In the specific implementation process, the composition ratio and process parameters can be gradually adjusted and optimized through multiple experiments and data analysis. For example, the grain size obtained from the initial experiment is 30 microns, which is close to the upper limit of the preset range. By reducing the sintering temperature to 850°C, the grain size obtained from the second experiment is 25 microns, which is closer to the median of the preset range, further improving the mechanical properties of the electrode substrate. In addition, the optimization of precipitate phase distribution can also be achieved by adjusting the cooling rate. For example, in the initial experiment, the cooling rate is 10°C / min, and the precipitate phase distribution is relatively concentrated. By increasing the cooling rate to 15°C / min, the precipitate phase distribution obtained from the second experiment is more uniform, and the electrical conductivity is significantly improved. The control of dislocation density is more complex and requires comprehensive consideration of the influence of composition ratio and process parameters. For example, by increasing the proportion of cobalt element to 15% and using a segmented heating method during sintering, the dislocation density can be effectively reduced, and the toughness of the material can be improved. In summary, by precisely controlling the grain size, precipitate phase distribution, and dislocation density, the microstructure of the alloyed electrode substrate can be optimized at the micro level, thereby improving its macro performance. This method not only improves the overall performance of the electrode substrate, but also reduces production costs and enhances market competitiveness. Through data-driven and experimental verification, the traditional trial-and-error method is avoided, making the production process more scientific and controllable. In practical applications, the optimization strategy can also be adjusted according to specific requirements. For example, if the electrical conductivity requirement is higher, the weight of the uniformity of the precipitate phase distribution can be increased during the optimization process, so that the optimization process tends to find a parameter combination with better electrical conductivity. This flexibility and adjustability make this method adaptable to different production requirements and environmental changes.By acquiring the preset range of ideal microstructure parameters, detecting the microstructure parameters of the sample, comparing and optimizing the component proportion and process parameters, the alloyed electrode base with ideal microstructure is finally prepared, and this series of steps constitutes a complete and efficient production optimization process, which provides strong technical support for the production of alloyed electrode base.

[0024] In step S103, the high-temperature toughness level of the alloyed electrode base sample with ideal microstructure is characterized by high-temperature tensile test and high-temperature creep test, and the conductivity is tested by four-probe method; whether the high-temperature toughness level and the conductivity meet the preset index is judged, if yes, it is determined that the alloyed electrode base can maintain stable comprehensive performance in high-temperature environment, and the preset index includes yield strength not less than 200 MPa and conductivity not less than 40% IACS at 600℃.

[0025] The microstructure parameters of the alloyed electrode base sample are acquired, including grain size and precipitate distribution; the microstructure characteristics are obtained by analyzing the microstructure parameters by image processing algorithm; the stress-strain curve and the creep curve are acquired by performing tensile test and creep test on the alloyed electrode base sample in high-temperature environment; the high-temperature toughness index and the conductivity index are input into the prediction model to judge whether the preset yield strength threshold and the conductivity threshold are met; if the preset threshold is met, it is determined that the alloyed electrode base meets the high-temperature comprehensive performance requirement; if not, the component and preparation process of the alloyed electrode base are adjusted, the sample is re-acquired and the performance is evaluated.

[0026] Specifically, obtaining the microstructure parameters of the alloyed electrode substrate sample first requires detailed observation of the sample by high-resolution transmission electron microscopy (HRTEM) and scanning electron microscopy (SEM). For example, the grain size can be determined by measuring the grain boundaries in the SEM image, assuming that the grain size distribution of a certain sample is between 50 nanometers and 200 nanometers. The precipitate phase distribution can be analyzed by coherent diffraction spots in the HRTEM image to determine the type and distribution of the precipitate phase, such as the nanoscale CuAl 2 phase uniformly distributed in the matrix in a certain sample. Image processing algorithms are used to analyze the microstructure parameters, specifically using image processing libraries in MATLAB or Python, such as OpenCV, to preprocess, edge detect, and region segment the SEM and HRTEM images, thereby extracting the characteristic parameters of the grain size and precipitate phase distribution. For example, the grain boundaries are identified by edge detection algorithms to calculate the average size and distribution range of the grains; the precipitate phase is identified by region segmentation algorithms to calculate the area fraction and distribution uniformity. Tensile testing and creep testing of the alloyed electrode substrate sample in a high-temperature environment are usually performed in a high-temperature test furnace, with a temperature setting of 600°C or higher. Tensile testing is performed by a universal testing machine, and the stress-strain curve is recorded to extract indicators such as yield strength, tensile strength, and elongation. For example, the yield strength of a certain sample at 600°C is 250 MPa, the tensile strength is 300 MPa, and the elongation is 20%. The creep test records the change of strain with time under constant stress, draws the creep curve, and analyzes the creep rate and creep fracture time. For example, the creep rate of a certain sample under a stress of 100 MPa is 10^-7 s^-1, and the creep fracture time is 100 hours. The high-temperature toughness indicators and electrical conductivity indicators are input into the prediction model, which can be a regression model based on machine learning, such as support vector regression (SVR) or neural network (NN), trained by historical data. The input indicators include yield strength, tensile strength, elongation, creep rate, and electrical conductivity, and the model outputs whether it meets the preset yield strength threshold and electrical conductivity threshold. For example, the preset yield strength threshold is 200 MPa, and the electrical conductivity threshold is 80% IACS (International Annealed Copper Standard), and the model prediction result shows that the yield strength of a certain sample is 250 MPa and the electrical conductivity is 85% IACS, which meets the preset threshold. If it meets the preset threshold, the alloyed electrode substrate meets the high-temperature comprehensive performance requirements and can be mass-produced and applied. For example, the alloyed electrode substrate can be used as an electrode material for high-temperature fuel cells, which can significantly improve the efficiency and service life of the battery due to its excellent high-temperature toughness and electrical conductivity. If it does not meet the requirements, the composition and preparation process of the alloyed electrode substrate are adjusted, the sample is re-acquired, and the performance is evaluated. Adjusting the composition may include increasing or decreasing the content of certain alloying elements, such as increasing the content of Cu to improve electrical conductivity and reducing the content of Fe to reduce grain size.The adjustment of the preparation process can include changing the heat treatment temperature and time, such as increasing the annealing temperature from 500°C to 600°C and extending the holding time from 1 hour to 2 hours, to optimize the microstructure. After re-acquiring the sample, the above microstructure analysis and performance test steps are repeated until the preset performance requirements are met. The reason for this is that the microstructure of the alloyed electrode base directly determines its macroscopic performance, and by precisely controlling the grain size, precipitate distribution and dislocation density, the high-temperature toughness and electrical conductivity of the material can be significantly improved. High-temperature tensile and creep tests can truly reflect the performance of the material in the actual working environment, and the introduction of the prediction model greatly improves the efficiency and accuracy of performance evaluation. By continuously adjusting the composition and process parameters, an alloyed electrode base that meets the high-temperature comprehensive performance requirements is finally obtained, ensuring its reliability and stability in high-temperature applications. Through the above analysis and examples, the technical principles and implementation methods of each step, as well as their logical relationships and mutual supporting effects, can be seen, which together ensure the excellent performance of the alloyed electrode base in high-temperature environments.

[0027] In step S104, for the alloyed electrode base sample, a pressurization experiment is performed in a high-pressure container to obtain the variation law of the compressive strength and yield strength with pressure; according to the maximum pressure under the actual use condition, it is judged whether the sample meets the high-pressure resistance requirement.

[0028] The material properties of the alloyed electrode base sample are obtained, the pressure range and pressurization step of the high-pressure container are determined, and the pressurization experiment scheme is formulated. The sample is placed in the high-pressure container, the pressure is gradually increased, and the pressure is kept at each pressure point until the sample deformation is stable, then the compressive strength data is recorded; continue to increase the pressure until the sample yields, and record the yield strength data. According to the maximum pressure under the actual working condition, the critical values of compressive strength and yield strength are determined on the strength-pressure curve. It is judged whether the compressive strength and yield strength of the sample are higher than the critical values, if yes, it is determined that the high-pressure resistance requirement is met.

[0029] Specifically, obtaining the material properties of the alloyed electrode base sample is the basic link of the experiment. Material properties include but are not limited to density, hardness, elastic modulus, etc. For example, the density of a certain alloyed electrode base sample is 7.8 g / cm 3, hardness of HB300, and elastic modulus of 210 GPa. These parameters provide foundational data for subsequent compression performance testing, aiding in understanding and predicting material behavior under different pressures. Determining the pressure range and pressurization step size for the high-pressure vessel is crucial for experimental design. Assuming the highest pressure required for the experiment is 500 MPa, considering safety and equipment capacity, the pressure range can be set to 0-500 MPa. The pressurization step size is determined based on the expected response of the material and experimental precision requirements, for example, choosing a step size of 10 MPa per step allows for detailed observation of material behavior under different pressures while avoiding loss of detail due to large step sizes. Place the sample in the high-pressure vessel and gradually increase the pressure, maintaining the pressure at each point until the sample deformation stabilizes, then record the compression strength data. For example, when the pressure reaches 100 MPa, maintain the pressure for 10 minutes and record the sample deformation and stress-strain curve at this time. Continue to increase the pressure to 200 MPa, 300 MPa, etc., and repeat the above steps until 500 MPa or the sample yields. According to the maximum pressure under actual working conditions, determine the compression strength and yield strength critical values on the strength-pressure curve. Assuming the maximum pressure under actual working conditions is 300 MPa, find the corresponding compression strength and yield strength values on the strength-pressure curve. For example, if the compression strength of the sample is 250 MPa and the yield strength is 200 MPa at 300 MPa, these two values are the critical values. Determine whether the compression strength and yield strength of the sample are higher than the critical values. If the actual compression strength of the sample under 300 MPa is 260 MPa and the yield strength is 210 MPa, both are higher than the critical values of 250 MPa and 200 MPa, then it is determined that the high-pressure resistance requirement is met. The specific implementation method is as follows: 1. Material property testing: measure sample density using a density meter, hardness using a hardness tester, and elastic modulus using a universal testing machine. 2. High-pressure vessel preparation: select a high-pressure resistant container that can withstand at least 500 MPa pressure. 3. Pressurization experiment: place the sample in the container and use a hydraulic pump to gradually increase the pressure, maintaining the pressure for 10 minutes every 10 MPa increase and recording the data. 4. Data recording and analysis: use a stress-strain tester to record the data and plot the strength-pressure curve to determine the critical values. 5. Result determination: compare the actual strength with the critical values to determine whether the sample meets the high-pressure resistance requirement. Through the above steps, the performance of the alloyed electrode base sample under high-pressure environment can be systematically evaluated to ensure its reliability in actual application. For example, a sample that performs well in compression and yield strength tests proves its structural stability under high-temperature and high-pressure environments, making it suitable for high-temperature electrode material applications. The advantage of this method is that it can accurately control pressure changes and observe material behavior under different pressures in detail, providing reliable data support for material design and process optimization.In addition, through multi-step and multi-pressure point testing, the compression resistance of the material can be comprehensively evaluated, avoiding misjudgment caused by a single test point. In summary, through scientific and reasonable experimental design and rigorous data analysis, the high-pressure resistance of the alloyed electrode substrate sample can be effectively evaluated, ensuring its stability and reliability in high-temperature and high-pressure environments, providing strong support for practical applications.

[0030] Step S105, for the alloyed electrode substrate sample, immersion corrosion experiment and electrochemical impedance spectroscopy test are carried out, and by comparing with the pure substrate material, it is determined whether the alloying improves the corrosion resistance of the material, and the maximum use time in different corrosion media is obtained.

[0031] According to the material properties of the electrode substrate, the alloying method is selected, and the alloyed electrode substrate sample and the pure substrate sample are prepared. The electrochemical impedance data of the sample after immersion corrosion are obtained by using an electrochemical workstation. If the corrosion resistance of the alloyed electrode substrate is better than that of the pure substrate, the maximum use time of the material in different corrosion media is determined according to the mass loss rate. If the corrosion resistance of the alloyed electrode substrate is lower than that of the pure substrate, the reason for the decrease in corrosion resistance caused by alloying is judged by analyzing the electrochemical impedance spectroscopy data, and the alloying process parameters are optimized. The maximum use time of the alloyed electrode substrate in different corrosion media is obtained by comprehensively analyzing the immersion corrosion experiment and electrochemical impedance spectroscopy test results.

[0032] Specifically, according to the material properties of the electrode substrate, selecting a suitable alloying method is a key step to improve the performance of the electrode substrate. Assuming that the main component of a certain electrode substrate is nickel, in order to improve its corrosion resistance and mechanical properties, elements of chromium and molybdenum are selected for alloying. When preparing the alloyed electrode substrate sample, powder metallurgy method is used, and the specific steps include mixing nickel powder, chromium powder and molybdenum powder, pressing the green body, and sintering in a high-temperature vacuum furnace to obtain a uniform alloyed electrode substrate sample. At the same time, a pure nickel substrate sample is prepared as a control group. An electrochemical workstation is used to carry out immersion corrosion experiment. First, the alloyed electrode substrate sample and the pure substrate sample are immersed in a simulated corrosion medium, such as a 3.5% sodium chloride solution, to simulate seawater corrosion environment. Through electrochemical impedance spectroscopy (EIS) test, the electrochemical impedance data of the sample at different immersion times are obtained. Assuming that after 24 hours of immersion, the impedance value of the alloyed electrode substrate is 5000Ω, and the impedance value of the pure substrate sample is 3000Ω, which indicates that the alloyed electrode substrate has higher corrosion resistance. If the corrosion resistance of the alloyed electrode substrate is better than that of the pure substrate, the maximum use time of the material in different corrosion media is further determined by the mass loss rate. Assuming that in the sodium chloride solution, the mass loss rate of the alloyed electrode substrate is 0.1mg / cm 2 ·, and the mass loss rate of the pure substrate is 0.2mg / cm 2· days. Based on this data, it can be concluded that the maximum service time of the alloyed electrode substrate in a specific corrosive environment is 1000 days, while the maximum service time of the pure substrate is 500 days. If the corrosion resistance of the alloyed electrode substrate is lower than that of the pure substrate, the reason for the decrease in corrosion resistance caused by alloying needs to be determined by analyzing the electrochemical impedance spectroscopy data. Assuming that in the EIS test, the impedance value of the alloyed electrode substrate is lower than that of the pure substrate, and multiple time constants appear in the impedance spectrum, indicating that a non-uniform corrosion product film may have formed during the corrosion process. Through scanning electron microscopy (SEM) and energy dispersive spectroscopy (EDS), it is found that there are enrichment areas of chromium and molybdenum in the corrosion product film, leading to uneven electrochemical activity and thus reducing the corrosion resistance. To address this issue, the alloying process parameters are optimized, such as adjusting the addition ratio of chromium and molybdenum, or using a more uniform sintering process to improve the uniformity and stability of the corrosion product film. Combining the results of immersion corrosion experiments and electrochemical impedance spectroscopy tests, the maximum service time of the alloyed electrode substrate in different corrosive media can be obtained. For example, in a sodium chloride solution, the mass loss rate of the optimized alloyed electrode substrate is reduced to 0.05 mg / cm 2 · day, and the maximum service time is extended to 2000 days. This result not only provides important reference for material selection and application, but also shows that through reasonable alloying process optimization, the corrosion resistance of the electrode substrate can be effectively improved. When selecting the alloying method, the types and addition ratios of alloying elements, as well as the effects of preparation process on the microstructure and properties of the material, need to be considered. For example, the addition of chromium elements can form a dense oxide film to improve corrosion resistance, while the addition of molybdenum elements can enhance the mechanical strength and high-temperature resistance of the material. Through powder metallurgy, the uniform distribution of alloying elements can be ensured, and the performance unevenness caused by composition segregation can be avoided. Electrochemical impedance spectroscopy is an important means to evaluate the corrosion resistance of materials. By measuring the impedance value of the sample at different frequencies, the impedance spectrum of the material can be obtained. The Nyquist plot composed of the real and imaginary parts of the impedance spectrum and the Bode plot of the phase angle changing with frequency can directly reflect the electrochemical behavior and corrosion mechanism of the material. For example, the size and shape of the capacitive arc in the Nyquist plot can reflect the properties and thickness of the corrosion product film, while the peak value of the phase angle in the Bode plot can represent the charge transfer resistance in the corrosion process. The calculation of the maximum service time of the material in different corrosive media based on the mass loss rate is a quantitative evaluation method based on the corrosion rate. Assuming that the corrosion rate of the material in a certain corrosive medium is v (unit: mg / cm 2 · day), the maximum service time T (unit: day) can be calculated by the formula T = δ / v, where δ is the allowed corrosion depth of the material (unit: mg / cm 2). This method is simple and intuitive, and is suitable for rapid evaluation of the corrosion resistance and service life of materials. When optimizing alloying process parameters, the interactions of alloying elements, the influence of preparation process on microstructure, and the requirements of actual application environment should be considered comprehensively. For example, by adjusting the sintering temperature and time, the grain size and phase composition of the alloyed electrode substrate can be controlled, which in turn affects its corrosion resistance. Through SEM and EDS analysis, the morphology and composition of the corrosion product film can be observed directly, providing a basis for process optimization. In summary, through systematic experimental design and data analysis, the corrosion resistance of the alloyed electrode substrate can be evaluated comprehensively, the alloying process parameters can be optimized, and the reliability and service life of the material in practical application can be improved. This method not only provides reliable data support for material design and process optimization, but also provides an important reference for material selection and use in practical applications.

[0033] Step S106, in a simulated use environment of high temperature, high pressure, and strong corrosion multi-factor coupling, long-term working test is carried out on the alloyed electrode substrate sample, and the organization structure evolution law of the alloyed electrode substrate sample in the complex harsh environment is obtained; a quantitative relationship model of the organization structure parameters and the use time is established by using a machine learning algorithm, and the service life of the electrode substrate is predicted.

[0034] For the organization structure evolution data, data preprocessing techniques are used for cleaning and standardization processing to remove abnormal values and noise data, obtaining high-quality machine learning model training data; according to the training data, a support vector machine or a random forest machine learning algorithm is used to establish a quantitative model of the organization structure parameters and the use time, and through model training and optimization, the prediction accuracy of the quantitative model is improved; the optimized alloyed electrode substrate is put into practical application, the tracking monitoring data of the alloyed electrode substrate in the actual use environment is obtained, and the monitoring data is used to further optimize the quantitative model, forming a model optimization closed loop, and continuously improving the service performance and life of the alloyed electrode substrate.

[0035] Specifically, for the organizational structure evolution data, first need to carry on the data preprocessing technology to carry on the cleaning and standardization processing. Data preprocessing is the key step to ensure the quality of machine learning model training data. For example, assume that there is a set of data about the organizational structure evolution of alloy electrode matrix under different temperature and time conditions, these data may contain experimental errors, abnormal values caused by equipment failure and environmental noise, etc. Through data cleaning, statistical methods such as box plot analysis can be used to identify and eliminate abnormal values that deviate significantly from the normal range. Further, standardization processing can convert data of different dimensions to the same scale, and common methods such as Z-score standardization can make the mean of data 0 and the standard deviation 1, so as to eliminate the influence of dimension and facilitate subsequent model training. After obtaining high-quality training data, support vector machine (SVM) or random forest (RF) machine learning algorithm is used to establish the quantitative model of organizational structure parameters and service time. Support vector machine finds the optimal hyperplane to maximize the classification interval of samples, which is suitable for classification and regression problems of small sample and high-dimensional data. For example, the radial basis function (RBF) kernel in SVM can be selected, and the optimal parameters are determined by cross-validation to establish the regression model between organizational structure parameters (such as grain size, phase composition, etc.) and service time. Random forest constructs multiple decision trees and votes or averages to improve the generalization ability of the model. Assuming that the random forest algorithm is used, the same quantitative model is established by optimizing parameters such as the number of trees and the maximum depth through grid search. Model training and optimization are the key steps to improve prediction accuracy. For example, through cross-validation method, the data set is divided into training set and validation set, and the model parameters are adjusted repeatedly until the best combination of model parameters is found. Further, indicators such as confusion matrix and mean square error (MSE) can be used to evaluate the performance of the model to ensure that the prediction accuracy of the model meets the requirements of practical application. The optimized alloy electrode matrix is put into practical application to obtain its tracking monitoring data in the actual use environment. For example, assume that the alloy electrode matrix is applied to the electrolytic cell of a certain chemical equipment, and the temperature, current density, corrosion rate and other key parameters are monitored in real time by installing sensors. These monitoring data not only reflect the performance of the alloy electrode matrix in the actual environment, but also provide valuable data support for further optimization of the model. The monitoring data is used to further optimize the quantitative model, forming a model optimization closed loop. For example, by comparing and analyzing the actual monitoring data and the model prediction data, it is found that the model prediction deviation is larger under certain conditions. By analyzing the causes of these deviations, such as changes in environmental factors and material aging, the model is iteratively optimized. New feature variables can be introduced, the model structure can be adjusted, and even more suitable algorithms can be replaced to continuously improve the prediction accuracy and generalization ability of the model. This closed-loop optimization process not only improves the performance and service life of the alloy electrode matrix, but also provides a strong guarantee for its reliability in practical application.For example, by continuously optimizing the model, the maximum service time of the alloy electrode base in different corrosion media can be more accurately predicted, so that more scientific maintenance and replacement strategies can be developed, reducing equipment failure and downtime and improving production efficiency. Through the close cooperation and iterative optimization of each link, a high-efficiency and reliable alloy electrode base performance prediction and optimization system is finally formed. Data preprocessing ensures the quality of model training data, machine learning algorithms establish a scientific quantitative model, and tracking and monitoring data in actual application provide real-time feedback for model optimization, and the closed-loop optimization mechanism continuously improves the prediction accuracy of the model and the actual application effect. This systematic approach not only improves the performance and service life of the alloy electrode base, but also provides strong technical support for material research and application in related fields.

[0036] Step S107, a full-process database of alloyed electrode base from preparation, characterization to use is established, big data analysis and machine learning algorithms are used to mine the internal relationship between preparation process, microstructure and use performance; according to the analysis results, the material composition and process parameters are optimized to realize the simultaneous improvement of the toughness and conductivity of the electrode base.

[0037] Obtain the preparation process, characterization data and use performance of the alloyed electrode base, establish a full-process database; preprocess the data in the database, and establish a prediction model between the preparation process, microstructure and use performance by machine learning algorithm; according to the prediction model, determine the key influencing factors and the optimal parameter range, and optimize the material composition and process parameters; use the optimized material composition and process parameters to prepare the alloyed electrode base sample, feed the test and characterization data back to the database, and iteratively update the prediction model until the toughness and conductivity of the electrode base are simultaneously improved.

[0038] Specifically, the preparation process, characterization data, and performance of the alloyed electrode matrix are obtained, and a full-process database is established to comprehensively understand the entire process from raw material selection to final application. Taking nickel-cobalt-manganese lithium oxide (NMC) ternary positive electrode material as an example, its preparation process includes steps such as ball milling mixing, spray drying, and high-temperature sintering. Characterization data includes particle size distribution, crystal structure, specific surface area, etc., and performance includes electrochemical capacity, cycle stability, rate performance, etc. Integrating these data into the database can facilitate data analysis and model construction. Preprocessing of data in the database is necessary to ensure data accuracy and consistency. Taking particle size distribution data as an example, there may be outliers due to measurement errors. Through box plot analysis, data points outside the range of 1.5 times IQR are removed, and then standardized to make the data conform to the normal distribution, facilitating the input of subsequent machine learning models. By establishing a prediction model between the preparation process, microstructure, and performance using machine learning algorithms, support vector machines (SVM) or random forests (RF) can be chosen. Assuming the use of random forest algorithm, input features include ball milling time, sintering temperature, particle size distribution, crystal structure parameters, etc., and output targets are electrochemical capacity and cycle life. Through cross-validation and grid search optimization of model parameters such as the number of trees and maximum depth, the best prediction model is obtained. According to the prediction model, the key influencing factors and optimal parameter range are determined, which can further optimize material composition and process parameters. For example, the model shows that the electrochemical capacity is highest at a sintering temperature of 800°C, but the cycle life is best at 750°C. Through multi-objective optimization algorithms such as NSGA-II, the optimal temperature range that balances capacity and life is found, such as 760-780°C. Using the optimized material composition and process parameters to prepare the alloyed electrode matrix sample can significantly improve material performance. Taking NMC as an example, after adjusting the cobalt content and sintering temperature, the prepared electrode matrix shows higher initial capacity and better cycle stability in laboratory tests. Feedback of test and characterization data to the database forms a data closed loop, which can continuously iterate and update the prediction model. In the specific implementation process, first, optimize the material composition. Assuming the original formula is Ni:Co:Mn=8:1:1, through model analysis, it is found that increasing the cobalt content to Ni:Co:Mn=7:2:1 can improve the conductivity and cycle performance of the electrode matrix. Then, optimize the ball milling time and sintering temperature, extend the ball milling time from 10 hours to 12 hours, and adjust the sintering temperature from 750°C to 770°C to further refine the particle size and improve the crystallinity. Feedback of test and characterization data is crucial. Assuming that the newly prepared electrode matrix has a capacity retention rate of 90% after 500 cycles, which is 5% higher than before optimization, these data are entered into the database, and the model will adjust the parameter weights based on the new data to improve the prediction accuracy. Through multiple iterations, the prediction accuracy and performance of the model gradually improve.This full-process database and prediction model not only effectively guides material preparation and process optimization, but also significantly shortens the research and development cycle and reduces experimental costs. Through data-driven methods, the optimal combination of material and process parameters can be quickly found based on a large amount of experimental data, avoiding the waste of resources caused by traditional trial-and-error methods. In practical applications, this optimization method can be widely applied to the development of various alloyed electrode substrates. For example, in the field of lithium-ion batteries, by optimizing the composition and preparation process of the positive electrode material, the energy density and cycle life of the battery can be significantly improved; in the field of fuel cells, by optimizing the composition and preparation process of the catalyst, the electrocatalytic activity and stability can be improved. The progress of these technologies will provide strong support for the development of new energy industries. Through this systematic data analysis and model prediction method, not only can the toughness and conductivity of the electrode substrate be improved, but also can provide reference for the development and optimization of other material systems. The core of this method is the comprehensiveness of the data and the accuracy of the model. Only on the basis of high-quality data, a reliable prediction model can be built to guide actual production and application. In actual operation, attention should be paid to the timeliness of the data and the adaptability of the model. With the continuous emergence of new materials and new processes, the database and model also need to be updated and maintained to ensure the accuracy and practicality of the prediction results. Through continuous optimization and iteration, the comprehensive performance of the alloyed electrode substrate can be continuously improved to meet the growing industrial demand.

[0039] It should be apparent to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments as described herein, and that the application can be implemented in other embodiments that are within the scope and spirit of the application. The foregoing embodiments are therefore to be considered in all respects as illustrative only and not restrictive in any way. The scope of the application is thus indicated by the appended claims rather than by the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. No feature of the application is to be construed as limiting in any way unless expressly so defined in the claims.

Claims

1. A method for developing electrode substrate materials, characterized in that, The method includes: The composition ratio and process parameters of the alloyed electrode matrix are acquired and used as training samples for a machine learning algorithm. For this training sample set, a nonlinear mapping model between composition, process, and performance is established using support vector regression. Based on this model, the optimal combination of composition ratio and process parameters balancing toughness and conductivity is determined. Alloyed electrode matrix samples prepared using the optimal combination of composition ratio and process parameters are obtained. For these samples, electron microscopy and X-ray diffraction are used to obtain microstructure parameters, including grain size, precipitate distribution, and dislocation density. It is determined whether these microstructure parameters meet a preset range. If so, the alloyed electrode matrix sample is determined to have an ideal microstructure. The preset range is determined based on target performance requirements and material design experience. For alloyed electrode matrix samples with an ideal microstructure, high-temperature tensile and high-temperature creep tests are used to characterize their high-temperature toughness, and a four-probe method is used to test their conductivity. It is determined whether the high-temperature toughness and conductivity meet preset indicators. If so, the alloyed electrode matrix is ​​determined to maintain stable comprehensive performance under high-temperature conditions. The preset indicators include 6... The yield strength at 00℃ is not less than 200MPa, and the conductivity is not less than 40% IACS. For alloyed electrode substrate samples, pressure tests are conducted in high-pressure containers to obtain the variation law of compressive strength and yield strength with pressure. Based on the maximum pressure under actual operating conditions, it is determined whether the sample meets the high-pressure resistance requirements. For alloyed electrode substrate samples, immersion corrosion tests and electrochemical impedance spectroscopy tests are conducted. By comparing with pure matrix materials, it is determined whether alloying improves the corrosion resistance of the material, and the maximum service time in different corrosive media is obtained. In a simulated service environment with multiple coupled factors of high temperature, high pressure, and strong corrosion, long-term working tests are conducted on alloyed electrode substrate samples to obtain the evolution law of its microstructure under complex and harsh environments. A quantitative relationship model between microstructure parameters and service time is established using machine learning algorithms to predict the service life of the electrode substrate. A full-process database of alloyed electrode substrates from preparation, characterization to use is established. Big data analysis and machine learning algorithms are used to explore the intrinsic relationship between preparation process, microstructure and performance. Based on the analysis results, material composition and process parameters are optimized to achieve a balance between improving the toughness and conductivity of the electrode substrate.

2. The method for developing electrode substrate materials according to claim 1, characterized in that, include: Historical production data of alloyed electrode substrates are obtained, including component ratios, process parameters, and performance test results. This historical production data is used as a training sample set for machine learning algorithms. The training sample set is preprocessed to remove outliers and normalize the numerical features to obtain the preprocessed training sample set. A nonlinear mapping relationship model of the alloyed electrode matrix properties is established by using the support vector regression algorithm, with the component ratios and process parameters in the preprocessed training sample set as input features and toughness and conductivity as output targets. Obtain a preset target range of toughness and conductivity values, and use the target range as a constraint condition for optimizing the nonlinear mapping relationship model; Using a grid search algorithm, under the given constraints, the optimal combination of component ratios and process parameters is searched to obtain candidate optimal parameter combinations; The candidate optimal parameter combination is input into the nonlinear mapping relationship model to predict the toughness and conductivity corresponding to the candidate optimal parameter combination; If the predicted toughness and conductivity meet the target value range, the candidate optimal parameter combination is determined as the optimal formula for producing the alloyed electrode matrix. If not, the process returns to execute the grid search algorithm to continue searching for the optimal parameter combination.

3. The method for developing electrode substrate materials according to claim 1, characterized in that, include: A preset range of ideal microstructure parameters for the alloyed electrode matrix is ​​obtained, including grain size, precipitate distribution, and dislocation density. Obtain the microstructure parameters of the alloyed electrode matrix sample, and compare the microstructure parameters with the preset range; If the microstructure parameters meet the preset range, then the optimized ratio and process parameters are determined to prepare an alloyed electrode matrix with an ideal microstructure.

4. The method for developing electrode substrate materials according to claim 1, characterized in that, include: The microstructure parameters of the alloyed electrode matrix sample are obtained, including grain size and precipitate distribution; The microstructure parameters are analyzed using image processing algorithms to obtain microstructure characteristics; Tensile and creep tests were performed on the alloyed electrode substrate sample under high temperature environment to obtain stress-strain curves and creep curves. Input the high-temperature toughness index and electrical conductivity index into the prediction model to determine whether they meet the preset yield strength threshold and electrical conductivity threshold. If the preset threshold is met, the alloyed electrode substrate is determined to meet the high-temperature comprehensive performance requirements. If the requirements are not met, the composition and preparation process of the alloyed electrode substrate are adjusted, and samples are obtained again and the performance is evaluated.

5. A method for developing electrode substrate materials according to claim 1, characterized in that, include: Obtain the material properties of the alloyed electrode substrate sample, determine the pressure range and pressurization step size of the high-pressure vessel, and formulate a pressurization experimental plan; The sample is placed in a high-pressure container, and the pressure is gradually increased. The pressure is maintained at each pressure point. After the sample deformation stabilizes, the compressive strength data is recorded. Continue to increase the pressure until the sample yields and deforms, and record the strength data of the yield. Based on the maximum pressure under actual working conditions, determine the critical values ​​of compressive strength and yield strength on the strength-pressure curve; Determine whether the compressive strength and yield strength of the sample are higher than the critical values. If so, it is determined that the high pressure resistance requirement is met.

6. The method for developing electrode substrate materials according to claim 1, characterized in that, include: Based on the material properties of the electrode substrate, an alloying method is selected to prepare alloyed electrode substrate samples and pure substrate samples; Electrochemical impedance data of the samples after immersion etching were obtained using an electrochemical workstation. If the corrosion resistance of the alloyed electrode substrate is better than that of the pure substrate, then the maximum service time of the material in different corrosive media can be determined based on the mass loss rate. If the corrosion resistance of the alloyed electrode substrate is lower than that of the pure substrate, the reason for the decrease in corrosion resistance due to alloying can be determined by analyzing the electrochemical impedance spectroscopy data, and the alloying process parameters can be optimized. Based on the combined results of immersion corrosion experiments and electrochemical impedance spectroscopy, the maximum service life of the alloyed electrode substrate in different corrosive media was obtained.

7. A method for developing electrode substrate materials according to claim 1, characterized in that, include: For the organizational structure evolution data, data preprocessing techniques are used to clean and standardize it, removing outliers and noisy data to obtain high-quality machine learning model training data. Based on the training data, a quantitative model of organizational structure parameters and usage time is established using support vector machine or random forest machine learning algorithms. The prediction accuracy of the quantitative model is improved through model training and optimization. The optimized alloy electrode substrate is put into practical application to obtain its tracking and monitoring data in the actual use environment. The monitoring data is then used to further optimize the quantitative model, forming a closed loop of model optimization, and continuously improving the performance and lifespan of the alloy electrode substrate.

8. A method for developing electrode substrate materials according to claim 1, characterized in that, include: Obtain the preparation process, characterization data, and performance of alloyed electrode substrates, and establish a full-process database; The data in the database is preprocessed, and a predictive model between the manufacturing process and microstructure and the performance is established using machine learning algorithms. Based on the prediction model, key influencing factors and optimal parameter ranges are determined, and material composition and process parameters are optimized. Alloyed electrode substrate samples are prepared using optimized material composition and process parameters. Test and characterization data are fed back to the database, and the prediction model is iteratively updated until both the toughness and conductivity of the electrode substrate are improved.

Images