Optimization method for metal surface laser cladding process parameters

Abstract

The invention provides an optimization method for metal surface laser cladding process parameters, and relates to the technical field of metal processing optimization, and the optimization method comprises the following process steps: step 1, determining an optimization target which is mainly used for determining a performance target of a cladding process and determining a quality target of the cladding process; 2, preliminary parameter selection and test design are mainly used for determining the cladding process parameter range and constructing a test model; step 3, test implementation and data acquisition; 4, data analysis and parameter optimization; and 5, verification and feedback adjustment are carried out. An orthogonal table is constructed by setting an orthogonal test, an optimal parameter combination is obtained by utilizing range analysis, a regression model equation can also be constructed by setting a response curved surface method test, and parameters are substituted into regression model parameters for operation, so that the optimal parameter combination can be obtained, the parameter optimization efficiency can be effectively improved, and the method is suitable for large-scale popularization and application. Meanwhile, records and experiences can be formed, and the method is widely applied to production practice.

Description

Technical Field

[0001] The invention relates to the technical field of metal processing optimization, and in particular to a method for optimizing process parameters of metal surface laser cladding. Background Art

[0002] Laser cladding refers to a process in which external materials are added to the molten pool formed after laser irradiation of the substrate by synchronous or pre-placed materials, and the two are quickly solidified together to form a coating layer. Characteristics of laser cladding: The cladding layer has low dilution but strong bonding force, and is metallurgically bonded to the substrate. It can significantly improve the wear resistance, corrosion resistance, heat resistance, oxidation resistance or electrical properties of the substrate surface, thereby achieving the purpose of surface modification or repair, meeting the specific performance requirements of the material surface while saving a lot of material costs. Compared with surfacing, spraying, electroplating and vapor deposition, laser cladding has the characteristics of low dilution, dense organization, good bonding between coating and substrate, many suitable cladding materials, and large changes in particle size and content. Therefore, the application prospect of laser cladding technology is very broad.

[0003] The parameters involved in the laser cladding process mainly include laser power, laser scanning speed and powder feeding rate. The laser cladding effect can be changed by changing these parameters. However, when performing laser cladding on a specific metal, how to achieve the optimal combination of parameters is the most urgent problem to be solved in actual production and processing, because the optimal combination of parameters can not only further improve the performance of the product, but also reduce production costs. However, the current optimization method is mainly derived from production experience. This method of optimizing parameters is too inefficient and difficult to be widely used in production practice. Summary of the invention

[0004] (I) Technical problems to be solved: In view of the shortcomings of the prior art, the present invention provides a method for optimizing the process parameters of laser cladding on metal surfaces, which solves the problems that the parameters involved in the laser cladding process mainly include laser power, laser scanning speed and powder feeding rate. The laser cladding effect can be changed by changing these parameters. However, when performing laser cladding process on a specific metal, how to achieve the optimal combination of parameters is the most urgent problem to be solved in actual production and processing, because the optimal combination of parameters can not only further improve the performance of the product, but also reduce the production cost. However, the current optimization method is mainly derived from production experience. Such a method of optimizing parameters is too inefficient and difficult to be widely used in production practice.

[0005] (II) Technical Solution To achieve the above objectives, the present invention is implemented through the following technical solution: A method for optimizing process parameters of laser cladding on a metal surface, comprising the following process steps: Step 1: Clarify the optimization goal, which is mainly used to determine the performance goal of the cladding process and the quality goal of the cladding process; Step 2: Preliminary parameter selection and experimental design, mainly used to determine the range of cladding process parameters and build an experimental model; Step 3: Test implementation and data collection, mainly used to conduct tests to obtain specific data and record them; Step 4: Data analysis and parameter optimization, mainly used to analyze data and optimize parameters; Step 5: Verification and feedback adjustment, mainly used to verify the implementation of the test and make adjustments based on the feedback results.

[0006] Furthermore, the performance target in step 1 is determined according to the application scenario of the cladding component, and the quality target includes the bonding strength between the cladding layer and the substrate, the internal quality of the cladding layer and the surface quality of the cladding layer.

[0007] Furthermore, the range of process parameters that need to be determined in step 2 includes laser power, laser scanning speed, powder feeding rate, spot size and powder particle size, and the experimental method is an orthogonal experiment or a response surface method experiment.

[0008] Furthermore, the implementation of the test in step 3 includes preparing the laser cladding sample according to the selected test parameters and recording the parameters during the cladding test.

[0009] Furthermore, the data collection in step 3 includes collecting data according to the previously determined quality and performance testing methods and collecting data on organizational structure analysis.

[0010] Furthermore, in the organizational structure analysis, the microstructure of the cladding layer is observed through a metallographic microscope, metallographic photographs are taken, and grain size parameters and shape parameters are measured.

[0011] Furthermore, the data analysis method in step 4 includes range analysis and variance analysis or regression analysis.

[0012] Furthermore, the optimization parameters in step 4 are determined based on the data analysis results to determine the optimal parameter combination.

[0013] Furthermore, the verification test in step 5 is implemented, and the cladding samples are made using the optimized parameter combination for verification test.

[0014] Furthermore, the feedback adjustment in step 5 is mainly performed based on the results of the verification test. When it is found that a certain performance indicator of the cladding layer does not meet expectations, it is necessary to review the data analysis process and the optimization parameter determination method.

[0015] (III) Beneficial Effects The present invention provides a method for optimizing process parameters of laser cladding on metal surfaces. It has the following beneficial effects: In this scheme, an orthogonal table is constructed by setting up an orthogonal experiment, and the optimal parameter combination is obtained by using range analysis. The regression model equation can also be constructed by setting up a response surface method experiment, and the parameters are substituted into the regression model parameters for calculation. The optimal parameter combination can also be obtained, which can effectively improve the efficiency of parameter optimization, and can also form records and experience, and be widely used in production practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a schematic flow chart of a method for optimizing process parameters of metal surface laser cladding. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example: Figure 1 As shown, an embodiment of the present invention provides a method for optimizing process parameters of laser cladding on a metal surface, comprising the following process steps: Step 1: Define the optimization goal, which is mainly used to determine the performance goal and quality goal of the cladding process. The performance goal is determined according to the application scenario of the cladding component, and the quality goal includes the bonding strength between the cladding layer and the substrate, the internal quality of the cladding layer, and the surface quality of the cladding layer. For example, if it is used for wear-resistant parts, such as the hammer of a crusher in mining machinery, the goal may be to make the hardness of the cladding layer reach HRC60 or above and the friction coefficient lower than 0.3. If it is used for corrosion-resistant chemical equipment pipelines, the corrosion rate of the cladding layer in a specific corrosive medium (such as a 30% sulfuric acid solution) should be less than 0.1mm / year. For some parts that need to withstand high temperatures, such as aircraft engine blades, the high temperature resistance of the cladding layer is the key, and it may be required to maintain good organizational stability and oxidation resistance at a high temperature of 1000℃. The quality objectives include the bonding strength between the cladding layer and the substrate, the internal quality of the cladding layer (no defects such as pores and cracks) and the surface quality of the cladding layer (surface flatness and roughness). For example, for automobile engine parts, the bonding strength between the cladding layer and the substrate is required to reach more than 300MPa, and the surface roughness Ra value is less than 2μm. Step 2: Preliminary parameter selection and experimental design, mainly used to determine the range of cladding process parameters and build an experimental model. The range of process parameters that need to be determined includes laser power, laser scanning speed, powder feeding rate, spot size and powder particle size. The experimental method is orthogonal test or response surface method test; Determine the approximate range of process parameters based on material properties and past experience. For laser power, consider factors such as the melting point and thermal conductivity of the cladding material. For example, when cladding iron-based alloy powder onto a carbon steel substrate, the laser power may be initially set in the range of 1-3kW. The scanning speed is generally selected based on the cladding layer thickness requirements and production efficiency, which may be between 5-20mm / s. The powder feeding rate should match the laser power and scanning speed, which is approximately between 5-20g / min. For the spot size, if it is fine cladding, the spot size can be 0.5-1mm; for large-area cladding, the spot size can be 3-5mm. The powder particle size is also an important factor, generally between 15-150μm. Finer powder (15-45μm) is used for high-quality surface cladding, and coarser powder (45-150μm) is used for thicker cladding layers. Orthogonal test design: For the three factors of laser power, scanning speed and powder feeding rate, three levels are selected for each factor. The L9 (3^4) orthogonal test table can be used. In this way, only 9 groups of tests are needed to preliminarily examine the influence of each factor on the quality and performance of the cladding layer. In each group of tests, laser cladding is carried out according to the set parameters, and then the performance and quality of the cladding samples are tested; Response surface method experimental design: When it is necessary to study the influence of the interaction between factors on the cladding quality and performance, the response surface method is a good choice. It can describe the relationship between the response variables (such as cladding layer hardness, bonding strength) and factors (such as laser power, scanning speed) by establishing a mathematical model. For example, for a quadratic response surface model, the design test points include the center point, axis point and factorial point. The model is fitted through the data obtained from the experiment, and then the main effect and interaction effect of the factors are analyzed; Step 3: Test implementation and data collection, mainly used to conduct tests to obtain specific data and record them. Test implementation includes preparing laser cladding samples according to the selected test parameters and recording the parameters during the cladding test. Data collection includes data collection according to the previously determined quality and performance test methods and data collection for organizational structure analysis. In terms of organizational structure analysis, the microstructure of the cladding layer is observed through a metallographic microscope, metallographic photos are taken, and grain size parameters and shape parameters are measured; During the cladding process, it is necessary to ensure the stability of the equipment, such as the stable power output of the laser generator and the uniformity of the powder feeding device. For example, for the coaxial powder feeding system, it is necessary to regularly check whether the powder nozzle is blocked to ensure that the powder can be evenly distributed around the laser spot, because the actual parameters may deviate from the set parameters to a certain extent. These records are very important for subsequent data analysis; For appearance inspection, record the surface flatness, color consistency and defects of the cladding layer. For example, use a surface roughness meter to measure the surface roughness of different positions of the cladding layer and record its average value and fluctuation range. For mechanical property testing, record the hardness test results (such as hardness values ​​at different positions), the breaking load of the bonding strength test, the wear amount of the wear resistance test and other data. In the chemical property test, record the corrosion area and corrosion depth after the corrosion resistance test. Step 4: Data analysis and parameter optimization, mainly used to analyze data and optimize parameters. Data analysis methods include range analysis and variance analysis or regression analysis. The optimal parameter combination is determined based on the data analysis results. Range analysis: Range analysis can intuitively show the influence of each factor on the performance and quality indicators of the cladding layer. For example, in the analysis of the hardness index of the cladding layer, the range of the average hardness value of each factor at different levels is calculated. The larger the range, the greater the influence of the factor on the hardness. Through range analysis, the factors with greater influence on key indicators and their optimal levels can be preliminarily determined; ANOVA: ANOVA can more accurately evaluate the significance of factors. By calculating the variance and F value of each factor, it can be judged whether the factor has a significant effect on the index. If the F value is greater than the critical value, it means that the factor has a significant effect on the index. For example, in the variance analysis of the bonding strength index, it can be judged whether factors such as laser power, scanning speed and powder feeding rate have a significant effect on the bonding strength, and whether there is an interaction between the factors. Regression analysis (applicable to response surface method): Regression analysis is performed based on the data obtained from the response surface method experimental design to establish a mathematical model between the response variable and the factors. For example, a quadratic regression equation is established between the hardness of the cladding layer and the laser power, scanning speed and powder feeding rate. By analyzing the coefficients of the regression equation, the main effect and interaction effect of the factors can be understood, and the hardness of the cladding layer under different parameter combinations can be predicted through the equation; In the process of determining the optimal parameter combination, if it is found that the laser power has the most significant effect on the hardness of the cladding layer, and the hardness is highest at a higher level, and other indicators (such as bonding strength and surface quality) also meet the requirements, then a higher laser power level can be selected in the optimized parameter combination. Then, a verification test is carried out on the determined optimized parameter combination to ensure that the performance and quality of the cladding layer meet the expected goals; Step 5: Verification and feedback adjustment, mainly used to verify the implementation of the test and make adjustments based on the feedback results. The verification test is implemented, and the optimized parameter combination is used to make the cladding sample for verification test. The feedback adjustment is mainly based on the results of the verification test. When it is found that a certain performance indicator of the cladding layer does not meet expectations, it is necessary to review the data analysis process and the optimization parameter determination method. For example, it may be necessary to redesign the test, increase the level of factors, or change the experimental design method (such as changing from orthogonal experimental design to response surface method) to further optimize the process parameters until satisfactory cladding quality and performance goals are achieved; Use the optimized parameter combination to conduct a certain number of verification tests, such as making 3-5 cladding samples, and conduct comprehensive performance and quality inspections on these samples, including appearance inspection, organizational structure analysis, mechanical property testing, and chemical property testing. Compare the verification test results with the optimization goals. If the verification test results meet or exceed the optimization goals, it means that the optimized parameters are effective. If they do not meet the goals, the reasons need to be analyzed, which may be test errors, the influence of factors that were not considered, or inaccurate data analysis.

[0019] Test Example 1: Nickel-based alloy cladding of aircraft engine blades: Background and objectives: Aircraft engine blades work in high temperature, high stress and corrosive environment. Laser cladding of nickel-based alloys is used to improve the high temperature resistance, wear resistance and corrosion resistance of blades. The cladding layer is required to be well bonded with the substrate, without internal defects, and the hardness and high temperature oxidation resistance of the cladding layer meet specific standards.

[0020] Initial parameters and questions: The initial laser power was set to 2kW, the scanning speed was 10mm / s, and the powder feeding rate was 10g / min. It was found that there were pores and some unfused areas in the cladding layer. The bonding strength did not meet the requirements and the hardness was slightly lower than expected.

[0021] Optimization process: Experimental design: An orthogonal experimental design was adopted, and the factors were laser power (1.8kW, 2kW, 2.2kW), scanning speed (8mm / s, 10mm / s, 12mm / s) and powder feeding rate (8g / min, 10g / min, 12g / min).

[0022]

[0023] Data analysis: Through the range analysis, it is found that the laser power has the greatest influence on the hardness and bonding strength of the cladding layer, and the scanning speed has a significant effect on the porosity. With the increase of laser power, the hardness and bonding strength increase; the porosity decreases significantly when the scanning speed decreases.

[0024] Determination of optimization parameters: The final optimization parameters were determined to be laser power 2.2kW, scanning speed 8mm / s, and powder feeding rate 10g / min.

[0025] Optimization effect: After verification tests, the hardness of the cladding layer increased by about 15%, the bonding strength reached the expected requirements, the porosity was reduced to below 1%, and the high-temperature oxidation resistance was also significantly improved, meeting the use requirements of aircraft engine blades.

[0026] Test Example 2: Wear-resistant coating on die steel surface Background and objectives: The mold is prone to wear during use. By cladding WC-Co (tungsten carbide-cobalt) metal ceramic coating on the surface of mold steel, the wear resistance of the mold can be improved and the service life of the mold can be extended.

[0027] Initial parameters and questions: At the beginning, the laser power was set to 3kW, the scanning speed was 15mm / s, and the powder feeding rate was 15g / min. Cracks appeared in the cladding layer, and the surface roughness was large, which affected the molding accuracy of the mold.

[0028] Optimization process: Experimental design: An orthogonal experimental design was adopted, and the factors were laser power (2kW, 2.5kW, 3kW), scanning speed (16mm / s, 18mm / s, 20mm / s) and powder feeding rate (8g / min, 10g / min, 12g / min).

[0029]

[0030] Data analysis: Through the range analysis, it is found that the laser power has the greatest impact on the hardness and bonding strength of the cladding layer, and the scanning speed has a significant impact on the porosity. With the increase of laser power, the hardness and bonding strength increase; with the decrease of scanning speed, the porosity decreases significantly. Determination of optimized parameters: After optimization, the final parameters were determined as laser power 3kW, scanning speed 18mm / s, and powder feeding rate 12g / min.

[0031] Optimization effect: After optimization, the cracks in the cladding layer disappeared, and the surface roughness was reduced from the initial Ra6.0μm to about Ra3.0μm. The wear resistance test showed that the wear life of the mold was increased by about 2-3 times.

[0032] Test Example 3: Corrosion-resistant cladding on the surface of oil drill pipe: Background and objectives: Oil drill pipes work in the harsh corrosive environment underground. It is necessary to clad a layer of corrosion-resistant alloy on the surface of the drill pipe to improve its corrosion resistance.

[0033] Initial parameters and questions: The initial laser power was 1.5 kW, the scanning speed was 6 mm / s, and the powder feeding rate was 8 g / min.

[0034] The corrosion resistance of the cladding layer is insufficient, and local corrosion occurs in the simulated underground corrosion environment test.

[0035] Optimization process: The response surface method was used to design the experiment and the regression model was constructed to conduct the experiment. When studying the effect of laser cladding process parameters on the corrosion resistance of the cladding layer, it was assumed that the laser power ( )、Scanning speed( ) and powder feeding rate ( ) three main factors, and the second-order polynomial regression model is usually used to describe the relationship between corrosion resistance (y, which can be measured by indicators such as corrosion rate and corrosion resistance time) and these factors.

[0036] The second-order polynomial regression model form is:

[0037] Explanation of coefficient meaning Constant term : The theoretical base value of corrosion resistance is when the laser power, scanning speed, and powder feed rate are all zero. However, in actual laser cladding scenarios, these factors are usually not zero, but in the model it provides a benchmark reference for adjusting the impact of other factors on corrosion resistance.

[0038] Linear coefficient , , : represents a linear effect of laser power on corrosion resistance, e.g. if If it is negative, it means that with other factors unchanged, as the laser power increases, the corrosion resistance (for example, the corrosion rate) may decrease linearly; if it is positive, the corrosion resistance may increase linearly.

[0039] and Similar linear effects of scanning speed and powder feed rate on corrosion resistance are described respectively. For example, A positive value may indicate that within a certain range, as the scanning speed increases, the corrosion resistance increases; A negative value may indicate that the corrosion resistance tends to decrease when the powder feeding rate increases.

[0040] Quadratic coefficient , , : This reflects the effect of the quadratic term of laser power on corrosion resistance. is positive. With the increase of laser power, the corrosion resistance may show an accelerating enhancement (or accelerating weakening, depending on the linear coefficient and the overall model situation). The influence of this quadratic term reflects the possible nonlinear relationship. For example, the effect of too high or too low laser power on corrosion resistance may be non-monotonic.

[0041] same, and They represent the curvature effects of the quadratic terms of scanning speed and powder feeding rate on corrosion resistance, respectively, and are used to describe the possible nonlinear changes in corrosion resistance when these two factors change.

[0042] Interaction coefficient , , : This reflects the effect of the interaction between laser power and scanning speed on corrosion resistance. If it is positive, it means that when the laser power and scanning speed increase simultaneously, there is a synergistic enhancement effect on the corrosion resistance; if it is negative, there may be a situation of mutual cancellation, resulting in the change in corrosion resistance not being as expected when each factor is considered separately.

[0043] and These indicate similar effects of the interactions between laser power and powder feeding rate, and scanning speed and powder feeding rate on corrosion resistance, respectively.

[0044] Model building and estimation process Experimental design and data collection: First, a suitable response surface design method, such as central composite design (CCD) or Box-Behnken design (BBD), is used to determine different test points, i.e., different combinations of laser power, scanning speed, and powder feeding rate. For example, in a CCD design, there may be five levels (including the center level) for each factor, and multiple test points are formed by combining these levels.

[0045] A laser cladding test is carried out for each test point, and then the clad samples are placed in a specific corrosion environment (such as a salt spray test chamber, acid solution immersion) to measure corrosion resistance indicators (such as corrosion rate or corrosion resistance time). For example, at a certain test point, the laser power is 2KW, the scanning speed is 10mm / s, and the powder feeding rate is 10g / min. After the salt spray test, the corrosion rate is 0.1mm / year. These data are recorded as the data basis for model establishment.

[0046] Parameter estimates: Use statistical software or mathematical methods (such as the least squares method) to substitute the collected test data into the above regression model and solve for each coefficient , , …, The estimated values ​​of that minimize the sum of squared errors between the corrosion resistance values ​​predicted by the model and the actual measured values.

[0047] Verification and application of the model: Model test: The overall significance of the model is tested by analysis of variance (ANOVA). If the calculated F value and the corresponding p-value are less than the pre-set significance level (such as 0.05), it indicates that the model is significant as a whole, that is, the selected factors and their interactions have a significant effect on the corrosion resistance of the cladding layer. At the same time, a significance test is performed on each coefficient. For example, If its p-value is less than the significance level, it means that the interaction between laser power and scanning speed is significant on corrosion resistance, which helps to determine which factors and interactions need to be considered in actual process optimization.

[0048] Model application: After the model passes the test, it can be used to predict the corrosion resistance of the cladding layer under different process parameter combinations. For example, if you want to know the corrosion resistance of the cladding layer when the laser power is 2.2kW, the scanning speed is 12mm / s, and the powder feeding rate is 12g / min, substitute these parameter values ​​into the model to calculate the predicted value of corrosion resistance. In addition, response surface graphs and contour graphs can be drawn based on the model to intuitively analyze the interaction between factors and find the process parameter combination that achieves the best corrosion resistance, providing a basis for optimizing the laser cladding process.

[0049] Optimization parameters were determined: the optimized parameters were laser power 1.8kW, scanning speed 6mm / s, and powder feeding rate 8g / min.

[0050] Optimization effect: In the simulated downhole corrosion environment test, the corrosion resistance time of the optimized cladding layer was extended by about 50% compared with the initial cladding layer, effectively improving the corrosion resistance of the oil drill pipe.

[0051] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing process parameters of laser cladding on a metal surface, characterized in that: The process steps include: Step 1: Clarify the optimization goal, which is mainly used to determine the performance goal of the cladding process and the quality goal of the cladding process; Step 2: Preliminary parameter selection and experimental design, mainly used to determine the range of cladding process parameters and build an experimental model; Step 3: Test implementation and data collection, mainly used to conduct tests to obtain specific data and record them; Step 4: Data analysis and parameter optimization, mainly used to analyze data and optimize parameters; Step 5: Verification and feedback adjustment, mainly used to verify the implementation of the test and make adjustments based on the feedback results.

2. The method for optimizing process parameters of laser cladding on a metal surface according to claim 1, characterized in that: The performance target in step 1 is determined according to the application scenario of the cladding component, and the quality target includes the bonding strength between the cladding layer and the substrate, the internal quality of the cladding layer and the surface quality of the cladding layer.

3. The method for optimizing process parameters of laser cladding on a metal surface according to claim 1, characterized in that: The range of process parameters that need to be determined in step 2 includes laser power, laser scanning speed, powder feeding rate, spot size and powder particle size, and the test method is orthogonal test or response surface method test.

4. The method for optimizing process parameters of metal surface laser cladding according to claim 1, characterized in that: The implementation of the test in step 3 includes preparing the laser cladding sample according to the selected test parameters and recording the parameters during the cladding test.

5. The method for optimizing process parameters of laser cladding on a metal surface according to claim 1, characterized in that: The data collection in step 3 includes collecting data according to the previously determined quality and performance testing methods and collecting data on organizational structure analysis.

6. The method for optimizing process parameters of laser cladding on a metal surface according to claim 5, characterized in that: In the organizational structure analysis, the microstructure of the cladding layer is observed through a metallographic microscope, metallographic photographs are taken, and grain size parameters and shape parameters are measured.

7. The method for optimizing process parameters of metal surface laser cladding according to claim 1, characterized in that: The data analysis method in step 4 includes range analysis and variance analysis or regression analysis.

8. The method for optimizing process parameters of laser cladding on a metal surface according to claim 1, characterized in that: The optimization parameters in step 4 are determined based on the data analysis results to determine the optimal parameter combination.

9. The method for optimizing process parameters of laser cladding on a metal surface according to claim 1, characterized in that: In step 5, a verification test is performed, and a cladding sample is produced using the optimized parameter combination for the verification test.

10. The method for optimizing process parameters of metal surface laser cladding according to claim 1, characterized in that: The feedback adjustment in step 5 is mainly carried out based on the results of the verification test. When it is found that a certain performance indicator of the cladding layer does not meet expectations, it is necessary to review the data analysis process and the optimization parameter determination method.

Images