A Method and System for Directional Optimization of Investment Casting Parameters

Abstract

The present invention relates to a method and system for directionally optimizing investment casting parameters, belonging to the field of casting optimization. A quality monitoring database of investment casting workpieces mapped to the current parameter set is established, a directionally optimized target is configured, the target classification identifier in the directionally optimized target is determined, after selecting key optimization parameters using the main optimization target and the auxiliary optimization target, an analysis of the influence of the directionally optimized target of the key optimization parameters is performed, parameter optimization constraints are established according to the results of the analysis of the influence of the directionally optimized target, and then parameter directional optimization is performed. The directional optimization of investment casting parameters is completed using the results of the parameter directional optimization, solving the technical problems that the optimization of investment casting parameters lacks systematicness and comprehensiveness, it is difficult to achieve global optimality to improve the quality and production efficiency of castings, reduce production costs, and meet the market demand for high-quality castings.

Description

Technical Field

[0001] The present invention relates to the field of casting optimization, and particularly to a method and system for directionally optimizing investment casting parameters. Background Art

[0002] As a precision casting method, investment casting is widely used in many fields such as aerospace, petrochemical, and medical devices because it can produce castings with complex shapes, precise dimensions, and smooth surfaces. However, the investment casting process involves numerous parameters, such as wax pattern making parameters, melting parameters, pouring parameters, and subsequent heat treatment parameters. Minor changes in these parameters can have a significant impact on the quality of the final casting.

[0003] In the traditional investment casting process, the adjustment and optimization of parameters often rely on experience and the judgment of skilled workers. This method is not only inefficient but also difficult to ensure the stability and consistency of casting quality. With the continuous development of computer technology and optimization algorithms, people have begun to try to apply advanced information technology means to the parameter optimization of investment casting to achieve automation, intelligence, and precision in the casting process. Although there have been some studies and practices on the parameter optimization of investment casting, most of these methods focus on the adjustment of single parameters or the optimization of simple parameter combinations, lacking systematic and comprehensive consideration. In addition, these methods often ignore the mutual influence and restrictive relationship between different optimization objectives, resulting in the optimization results being difficult to achieve the global optimum. Summary of the Invention

[0004] Aiming at the technical problems in the prior art that the parameter optimization of investment casting lacks systematicness and comprehensiveness, it is difficult to achieve the global optimum to improve the quality and production efficiency of castings, reduce production costs, and meet the market demand for high-quality castings, the present invention provides a method and system for directionally optimizing investment casting parameters to solve these problems.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides a method for directional optimization of investment casting parameters. The method includes: obtaining the current parameter set of investment casting and establishing a quality monitoring database of investment casting workpieces mapped to the current parameter set; configuring directional optimization targets according to the quality monitoring database, where the directional optimization targets include porosity optimization, shell film thickness uniformity optimization, casting shrinkage rate optimization, and thermal stress crack optimization; determining the target classification identifiers in the directional optimization targets, where the target classification identifiers include main optimization targets, auxiliary optimization targets, and maintenance targets; after selecting key optimization parameters using the main optimization targets and auxiliary optimization targets, performing an impact analysis of the directional optimization targets on the key optimization parameters; establishing parameter optimization constraints based on the results of the directional target optimization impact analysis, and then performing parameter directional optimization, and completing the directional optimization of investment casting parameters using the results of the parameter directional optimization.

[0007] In a second aspect, the present invention provides a system for directional optimization of investment casting parameters. The system includes: a parameter acquisition module for obtaining the current parameter set of investment casting and establishing a quality monitoring database of investment casting workpieces mapped to the current parameter set; a target configuration module for configuring directional optimization targets according to the quality monitoring database, where the directional optimization targets include porosity optimization, shell film thickness uniformity optimization, casting shrinkage rate optimization, and thermal stress crack optimization; a classification identifier module for determining the target classification identifiers in the directional optimization targets, where the target classification identifiers include main optimization targets, auxiliary optimization targets, and maintenance targets; an impact analysis module for performing an impact analysis of the directional optimization targets on the key optimization parameters after selecting the key optimization parameters using the main optimization targets and auxiliary optimization targets; a directional optimization module for establishing parameter optimization constraints based on the results of the directional target optimization impact analysis, and then performing parameter directional optimization, and completing the directional optimization of investment casting parameters using the results of the parameter directional optimization.

[0008] The beneficial effects of the present invention are: by directionally optimizing the investment casting parameters, comprehensively considering multiple optimization targets such as porosity, shell film thickness uniformity, casting shrinkage rate, and thermal stress cracks, and classifying and processing different optimization targets, key parameters are accurately selected for impact analysis, and finally the precise adjustment of investment casting parameters is realized using the optimization results, significantly improving the quality of castings, production efficiency, and stability. Description of the Drawings

[0009] Figure 1 It is a flowchart of a method for directional optimization of investment casting parameters provided by the present invention.

[0010] Figure 2 It is a structural diagram of a system for directional optimization of investment casting parameters provided by the present invention.

[0011] Explanation of the reference numerals: parameter acquisition module 11 , target configuration module 12 , classification identification module 13 , impact analysis module 14 , directional optimization module 15 . DETAILED DESCRIPTION

[0012] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0015] Embodiment 1:

[0016] like Figure 1 As shown, an embodiment of the present invention provides a method for directional optimization of investment casting parameters, the method comprising:

[0017] S10: Acquire a current parameter set of investment casting, and establish a quality monitoring database of investment casting workpieces mapped with the current parameter set.

[0018] Among them, the monitoring indicators of the quality monitoring database include porosity, pore distribution, pore size, shell film thickness distribution, thickness standard deviation, shrinkage distribution, crack morphology, and crack size.

[0019] Exemplarily, investment casting is a precision casting technology. Its core equipment includes a wax injection machine for making wax patterns, an intermediate frequency induction furnace for metal melting, a pouring equipment for injecting molten metal into the wax pattern, and a heat treatment furnace for post-treatment of castings. The basic process of investment casting is as follows: First, use a wax injection machine to inject molten wax into a metal mold, and after cooling, a wax pattern is formed; then, coat the surface of the wax pattern with multiple layers of refractory coatings and harden them to form a shell mold; next, melt out the wax pattern in the shell mold, leaving a cavity; subsequently, inject the molten metal into the cavity through the pouring equipment, and after cooling and solidification, a casting is formed; finally, perform post-treatment processes such as cleaning and heat treatment on the casting to obtain the final product. The accuracy of the equipment and the control of the process play a crucial role in the quality of the casting throughout the entire process.

[0020] In this solution, in order to achieve precise control and optimization of casting quality, it is necessary to comprehensively obtain the current investment casting parameter set. These parameters cover all aspects from wax pattern making to metal pouring and subsequent processing, such as wax pattern forming temperature, metal melting temperature, pouring speed, and heat treatment process parameters. Subsequently, based on these parameter sets, a quality monitoring database mapped to them is established. This database details the key quality indicators of investment casting workpieces under each set of parameter combinations, including porosity (e.g., the porosity of a certain casting is less than 0.5%), pore distribution (uniform dispersion or concentration in a specific area), pore size (from tiny to a few micrometers), shell mold thickness distribution (uniformity, such as the average thickness deviation does not exceed 0.1 mm), thickness standard deviation (reflecting the consistency of the shell mold thickness), shrinkage rate distribution (whether the shrinkage of each part of the casting is uniform), crack morphology (such as linear cracks or reticular cracks), and crack size (tiny to almost invisible), etc. Through such a quality monitoring database, the specific impact of different parameter combinations on the casting quality can be intuitively understood, providing a data basis for subsequent optimization work. For example, when it is found that the porosity of a casting is relatively high under a certain set of parameters, relevant parameters can be adjusted according to the records in the database, such as reducing the pouring speed or optimizing the exhaust design of the wax pattern, in order to achieve the purpose of reducing porosity and improving the quality of the casting.

[0021] S20: Configure the directional optimization objectives according to the quality monitoring database. The directional optimization objectives include porosity optimization, shell mold thickness uniformity optimization, casting shrinkage rate optimization, and thermal stress crack optimization.

[0022] Optionally, a series of targeted optimization goals are further configured based on the established quality monitoring database. These goals serve to guide the improvement direction for subsequent casting processes. Specifically, the optimization goals cover porosity optimization, aiming to reduce the number and size of pores inside the casting. For example, reducing the porosity rate from the original 0.8% to below 0.5% to ensure the density of the casting; optimizing the shell film thickness uniformity to pursue precise control of the shell film thickness, with its standard deviation not exceeding 0.05 mm to ensure the consistency of the casting surface quality; optimizing the casting shrinkage rate, that is, adjusting the casting parameters to make the shrinkage rate of each part of the casting more uniform and avoid deformation and cracks, such as controlling the overall shrinkage rate within the range of ±0.2% of the predetermined value; and optimizing thermal stress cracks, aiming to reduce or eliminate cracks caused by thermal stress, especially for large and complex castings. For example, through precise heat treatment process control, the crack length is reduced to almost invisible. By setting optimization goals for these key quality indicators, the process parameters of investment casting can be adjusted targeted, thereby significantly improving the overall quality of the casting and meeting the manufacturing requirements of high precision and high performance.

[0023] S30: Determine the target classification identifier in the targeted optimization goal, and the target classification identifier includes the main optimization goal, the auxiliary optimization goal, and the maintenance goal.

[0024] Specifically, to ensure the comprehensiveness and efficiency of the optimization process, the targeted optimization goals are classified and identified. First, clarify the main optimization goal, which is the core point in the optimization task and represents the most critical and urgent quality problem currently. For example, in a specific project, if the high porosity rate is the main factor affecting the performance of the casting, then reducing the porosity rate will be set as the main optimization goal, and resources and efforts will be concentrated to significantly reduce the number and size of pores.

[0025] At the same time, set the auxiliary optimization goals. Although these goals are not as urgent as the main optimization goal, they are also indispensable factors for improving the quality of the casting. As secondary optimization goals, they assist in the realization of the main optimization goal. For example, while reducing the porosity rate, attention will also be paid to the uniformity of the shell film thickness to ensure it is within a reasonable deviation range to improve the surface quality and dimensional accuracy of the casting.

[0026] In addition, identify the maintenance goals, which aim to maintain the existing quality indicators at an acceptable level and avoid unnecessary negative impacts caused by the adjustment of the main and auxiliary optimization goals. For example, ensure that the shrinkage rate of the casting remains within a stable range during the optimization process to prevent the casting from deforming or generating new cracks due to excessive pursuit of other goals.

[0027] Through the target classification and identification, the optimization process can be more accurately guided, ensuring that each quality indicator is reasonably balanced during the optimization, and ultimately achieving an overall improvement in the investment casting process.

[0028] S40: After selecting the key optimization parameters using the main optimization objective and the auxiliary optimization objective, perform an analysis of the impact of the key optimization parameters on the directional optimization objective.

[0029] Preferably, in the key link of investment casting parameter optimization, first screen out the key optimization parameters that have the most significant impact on the casting quality according to the main optimization objective and the auxiliary optimization objective. These parameters are like sensitive switches affecting the casting quality, and their slight adjustment may bring a significant improvement in the casting quality. For example, if the main optimization objective is to reduce the porosity of the casting, the exhaust design of the wax pattern, the pouring temperature, and the chemical composition of the metal melting may be selected as the key optimization parameters because they directly affect the formation and quantity of the pores.

[0030] After selecting the key parameters, then perform an analysis of the impact of the key optimization parameters on the directional optimization objective. This step means using advanced simulation software and experimental data to deeply explore the specific impact of each key parameter on the main optimization objective and the auxiliary optimization objective. For example, by adjusting the exhaust design of the wax pattern, it can be observed how the porosity changes accordingly; at the same time, attention will also be paid to the possible chain reactions that this adjustment may have on other quality indicators such as the shell mold thickness uniformity and the casting shrinkage rate. Through such impact analysis, a relationship map between each key parameter and the casting quality can be clearly outlined, providing a scientific basis for subsequent optimization decisions.

[0031] S50: After establishing the parameter optimization constraints according to the results of the directional objective optimization impact analysis, perform parameter directional optimization, and use the results of the parameter directional optimization to complete the directional optimization of the investment casting parameters.

[0032] Specifically, after completing the analysis of the impact of the key optimization parameters on the directional optimization objective, construct the constraint conditions for parameter optimization based on these analysis results. These constraint conditions mean setting boundary lines for parameter adjustment to ensure that the expected objective will not be deviated from during the optimization process. For example, if it is found that a certain key parameter has a significant impact on the porosity but also affects the shell mold thickness uniformity, then set a constraint to keep the change in the shell mold thickness within an acceptable range while reducing the porosity.

[0033] Next, perform parameter-directed optimization. This process uses advanced optimization algorithms to automatically search for the optimal parameter combination under the set constraints. That is, to find the best parameter combination, the algorithm will continuously try different parameter combinations, evaluate their impact on the optimization goal, and gradually approach the optimal solution. Finally, use the results of parameter-directed optimization to complete the directed optimization of investment casting parameters. These optimized parameters are applied to actual production, which can significantly improve the quality of castings. For example, through the optimized parameter combination, the porosity of the casting may be successfully reduced by 30%, while maintaining the uniformity of the shell mold thickness, thereby greatly improving the density and surface quality of the casting and meeting the customer's requirements for high-quality castings.

[0034] In a preferred embodiment, after selecting the key optimization parameters using the primary optimization goal and the secondary optimization goal, perform an impact analysis of the directed optimization goal of the key optimization parameters, including: obtaining the set of adjustable parameters for investment casting; performing a quantitative mapping of the impact degree of the primary optimization goal and the secondary optimization goal on the set of adjustable parameters; constructing a goal impact matrix for all optimization goals in the directed optimization goal, where the goal impact matrix characterizes the mutual relationship between different optimization goals, and the mutual relationship includes a positive promotion relationship and a negative conflict relationship; calculating the sensitivity coefficient of the set of adjustable parameters based on the quantitative mapping of the impact degree and the goal impact matrix; and establishing the result of the impact analysis of the directed goal optimization based on the calculation result of the sensitivity coefficient.

[0035] In a specific embodiment, focus on accurately selecting the key optimization parameters using the primary optimization goal and the secondary optimization goal. Obtain the set of adjustable parameters for investment casting. These parameters are like variable factors in the casting process, and their adjustment will directly affect the quality of the casting. Then, perform a quantitative mapping of the impact degree of the primary optimization goal and the secondary optimization goal on the set of adjustable parameters. This process is like attaching an impact label to each parameter to clarify their contribution to each optimization goal.

[0036] To more comprehensively understand the relationship between parameters and optimization goals, construct a goal impact matrix for all optimization goals in the directed optimization goal. This matrix is like a network of relationships, clearly showing the positive promotion relationship and negative conflict relationship between different optimization goals. For example, reducing porosity may have a positive promotion relationship with improving the uniformity of the shell mold thickness, while having a negative conflict relationship with reducing thermal stress cracks. Furthermore, based on these quantitative mappings of the impact degree and the goal impact matrix, calculate the sensitivity coefficient of the set of adjustable parameters. By calculating the sensitivity coefficient, it is possible to determine which key optimization parameters have the greatest impact on the goal, thereby adjusting the weight of parameter optimization during the optimization process to prevent excessive or ineffective parameter adjustment.

[0037] Finally, based on the calculation results of the sensitivity coefficients, an analysis result of the directional target optimization impact is established, which will serve as an important basis for subsequent parameter directional optimization and optimization. For example, if it is found that a certain parameter is extremely sensitive to the porosity, then this parameter will be adjusted more carefully during the optimization process to ensure that while reducing the porosity, it will not have an adverse impact on other optimization goals. Through such a process, the directional optimization of investment casting parameters can be achieved more scientifically and accurately.

[0038] For example, there is currently an investment casting project that mainly focuses on the following three optimization goals: The main optimization goal is to reduce the porosity (target value: from the current 1.2% to below 0.8%); the auxiliary optimization goal is to improve the uniformity of the shell film thickness (target value: the thickness standard deviation is reduced from 0.15 mm to below 0.1 mm); the maintenance goal is to maintain the casting shrinkage rate within ±0.3%. Then, the following three adjustable parameters are selected for analysis. Among them, Parameter A: Wax pattern exhaust design (value range: 1 - 5, the larger the value, the more optimized the exhaust design); Parameter B: Pouring temperature (value range: 1500 - 1600 °C, step size 10 °C); Parameter C: Metal melting time (value range: 30 - 60 minutes, step size 5 minutes). Subsequently, a quantitative mapping table of the influence degree as shown in Table 1 is obtained (the value represents the change amount of the optimization goal when the parameter is adjusted by one unit):

[0039] Table 1: Quantitative mapping table of influence degree

[0040]

[0041] Furthermore, a target impact matrix is constructed as shown in Table 2 to show the mutual relationship between the optimization goals (simplified to a linear relationship here, which may be more complex in reality):

[0042] Table 2: Target impact matrix table

[0043]

[0044] Next, calculate the sensitivity coefficient of each parameter according to the influence degree quantization mapping and the target influence matrix (here, the simple weighted sum method is used, and the weights are set according to the importance of the optimization objectives. Assume that the weight of the porosity is 0.6, the weight of the shell film thickness uniformity is 0.3, and the weight of the shrinkage rate is 0.1). Then, the sensitivity coefficient of parameter A = 0.6×(-0.05) + 0.3×(-0.01) + 0.1×0.02 = -0.031; the sensitivity coefficient of parameter B = 0.6×(-0.03) + 0.3×0.02 + 0.1×(-0.01) = -0.017; the sensitivity coefficient of parameter C = 0.6×0.01 + 0.3×(-0.005) + 0.1×0.005 = 0.004. According to the calculation results of the sensitivity coefficients, the following conclusions can be drawn: Parameter A has the greatest impact on the optimization objective and is a negative impact, that is, increasing the value of parameter A (optimizing the exhaust design) can significantly reduce the porosity, and at the same time, it also helps to improve the shell film thickness uniformity, but it may slightly increase the shrinkage rate. The impact of parameter B is the second, and it is also a negative impact. However, when adjusting, the relationship between the reduction of porosity and the improvement of shell film thickness uniformity needs to be weighed. The impact of parameter C is the smallest and is a positive impact, but the contribution to the optimization objective is limited when adjusting. Based on the above analysis, parameter A (wax pattern exhaust design) can be adjusted first to significantly reduce the porosity and improve the shell film thickness uniformity. At the same time, parameter B (pouring temperature) can be appropriately adjusted to further optimize the porosity and shell film thickness uniformity, but attention needs to be paid to controlling the change of the shrinkage rate. The adjustment of parameter C (metal melting time) has a limited contribution to the optimization objective and can be fine-tuned after other parameters are adjusted in place.

[0045] In a preferred embodiment, the execution of parameter-directed optimization includes: after establishing the control interval of the parameters, creating an initial solution set based on the current parameter set; after performing the solution fitness evaluation within the initial solution set, establishing the optimization direction and optimization step size through the parameter optimization constraints and the fitness evaluation results; using the optimization direction and the optimization step size to iteratively update the initial solution set; and completing the parameter-directed optimization according to the iterative update results.

[0046] Preferably, during the process of parameter-oriented optimization, reasonable control intervals are set for each parameter. These intervals are like the "activity ranges" of the parameters, ensuring the effectiveness and safety of parameter adjustment. Then, an initial solution set is created based on the current parameter set. This solution set is like the "starting point" of parameter adjustment and contains multiple possible parameter combination schemes. Next, a fitness evaluation is performed on each solution in the initial solution set. This step is like "scoring" each scheme to evaluate their degree of satisfaction with the optimization goal. The optimization direction and optimization step size are established through the parameter optimization constraints and the fitness evaluation results. The parameter optimization constraints ensure the coordination of multi-objective optimization, making the optimization direction meet the requirements of the main optimization goal, taking into account the auxiliary optimization goal and the maintenance goal, and avoiding the phenomenon of being one-sided in the optimization process.

[0047] Subsequently, the initial solution set is iteratively updated using the optimization direction and the optimization step size. This process is a process of "gradually approaching" the optimal solution. In each iteration, the parameter combination is adjusted according to the optimization direction, and the adjustment amplitude is controlled according to the optimization step size to ensure that the parameter adjustment is both effective and stable. The parameter-oriented optimization is completed according to the iterative update results, thereby giving the optimal parameter combination scheme, which can significantly improve the quality of investment casting. For example, in a specific project, through parameter-oriented optimization, the porosity is successfully reduced by 20%, while the shell film thickness uniformity is improved, and the casting shrinkage rate is kept stable, thus greatly improving the overall performance and market competitiveness of the casting.

[0048] In a preferred embodiment, the iterative update of the initial solution set using the optimization direction and the optimization step size includes: establishing an iterative trajectory for each solution and identifying the iterative trajectory through the solution fitness value of each iteration; configuring an iterative evaluation interval, and identifying the update state of the iterative trajectory in the iterative evaluation interval to generate an evaluation classification, where the evaluation classification includes an optimal solution evaluation classification, an exploration evaluation classification, and a suboptimal solution evaluation classification; and performing search self-optimization management for iterative update according to the evaluation classification.

[0049] Exemplarily, during the process of iteratively updating the initial solution set using the optimization direction and the optimization step size, an iterative trajectory is established for each solution. These trajectories are like the "growth paths" of the solutions in the parameter space, recording every step change from their initial state to the current state. Furthermore, these iterative trajectories are identified through the solution fitness value of each iteration, making the performance of each solution in the optimization process clear at a glance.

[0050] In order to manage the iteration process more effectively, the iteration evaluation interval is configured. This interval is an evaluation scale used to measure the performance of the solution during the iteration process. Within the iteration evaluation interval, the update status of the iteration trajectory is identified and evaluation categories are generated. These evaluation categories include excellent solution evaluation category, exploration evaluation category, and poor solution evaluation category, which represent solutions with excellent performance, solutions worthy of further exploration, and solutions with poor performance, respectively.

[0051] Specifically, the solutions in the excellent solution evaluation category are those that have performed well in the current iteration and have significantly improved their fitness values. They are important candidates for finding the optimal solution. The solutions in the exploration evaluation category have certain potential, but may need further adjustment and optimization to tap their maximum value. The solutions in the poor solution evaluation category are those that have performed poorly in the current iteration, and their fitness values ​​have not significantly improved or even decreased. They may need to be replaced or readjusted.

[0052] Finally, we perform iterative and updated search self-optimization management based on these evaluation categories. For optimal solutions, we increase the search intensity and try to find better solutions near them; for exploratory solutions, we adjust the optimization strategy and encourage them to explore in more promising directions; and for inferior solutions, we consider replacing them or making substantial adjustments to them in order to achieve better performance in subsequent iterations.

[0053] In a preferred embodiment, the search self-optimization management that performs iterative updates based on the evaluation classification includes: configuring a local proxy model in the optimal solution evaluation classification, using the local proxy model to predict improvement trends, and generating a first reference optimization direction; configuring a penalty optimization identification layer in the inferior solution evaluation classification, using the penalty optimization identification layer to identify erroneous improvement directions, and establishing window improvement taboos; performing iterative fine-tuning updates on solutions within the optimal solution evaluation classification using the first reference optimization direction and window improvement taboos, performing mixed exploration iterative updates on the exploration evaluation classification using the first reference optimization direction and window improvement taboos, and configuring random factors to perform iterative updates on solutions within the inferior solution evaluation classification.

[0054] In detail, in the process of iteratively updating the search self-optimization management according to the evaluation classification, differentiated optimization strategies are adopted for solutions of different evaluation classifications. For the solutions in the evaluation classification of the best solution, a local proxy model is configured. This model can predict its improvement trend based on the performance of the current solution and generate the first reference optimization direction. This direction provides clear guidance for finding a better solution near the best solution. For the solutions in the evaluation classification of the worst solution, a penalty optimization recognition layer is configured. This recognition layer is like an error correction mechanism. It can identify the wrong direction of the solution in the improvement process and establish window improvement taboos to prevent the solution from falling into these wrong directions again in subsequent iterations.

[0055] Furthermore, the first reference optimization direction and window improvement tabu are used to fine-tune and iteratively update the solutions within the excellent solution evaluation classification. This process fine-tunes the parameter combinations, enabling the solutions to approach the optimal solution further while maintaining excellent performance. For the solutions in the exploration evaluation classification, a hybrid exploration iterative update strategy is adopted. Guided by the first reference optimization direction and window improvement tabu as well, but allowing the solutions to explore in a broader parameter space to discover potential optimal solution regions. For the solutions in the inferior solution evaluation classification, a random factor is configured to perform iterative updates. This random factor can introduce a certain degree of randomness during the improvement process of the solutions, helping the solutions break out of the current predicament and search for new improvement directions. Through self-optimizing management during the search, the performance of the excellent solutions can be enhanced, and at the same time, the inferior solutions can be gradually transformed into potential exploration solutions. Eventually, a globally optimal parameter combination is found, significantly improving the quality and production efficiency of the castings.

[0056] In a preferred embodiment, the execution of parameter directional optimization further includes: establishing an energy consumption evaluation function for the parameters; establishing a balance adaptation function based on the energy consumption evaluation function and the quality evaluation function; screening the optimization solution of the parameter directional optimization based on the balance adaptation function, and outputting the screening result of the optimization solution as the parameter directional optimization result.

[0057] Specifically, during the execution of parameter directional optimization, not only the impact of the parameters on the quality of the castings is concerned, but also an energy consumption evaluation function is introduced to consider the impact of parameter adjustment on energy consumption. The energy consumption evaluation function quantifies the energy consumption under different parameter combinations, helping to understand whether parameter adjustment will increase energy consumption while improving quality.

[0058] Based on the energy consumption evaluation function and the quality evaluation function, a balance adaptation function is jointly established. This function comprehensively considers the factors of both quality and energy consumption, ensuring that in the optimization process, neither the quality will be pursued one-sidedly while ignoring energy consumption, nor the quality will be sacrificed to reduce energy consumption. Furthermore, the optimization solution of the parameter directional optimization is screened based on this balance adaptation function. This process means screening out those solutions that meet the quality requirements and have low energy consumption from numerous possible parameter combinations. These solutions represent the best practices of parameter adjustment. Finally, the screening result of the optimization solution is output as the parameter directional optimization result. This result guides to find the optimal parameter combination solution, which not only improves the quality of the castings but also controls the energy consumption. By introducing the energy consumption evaluation function and establishing the balance adaptation function, the parameter combination solution can be successfully screened, achieving a win-win situation for both quality and energy consumption.

[0059] For example, in the investment casting process, the energy consumption mainly comes from the operation of heating equipment (such as furnaces, drying ovens, etc.). To simplify the problem, assume that the energy consumption is mainly related to the heating time and heating temperature. Therefore, the energy consumption evaluation function can be expressed as: E = α×T×t + β; where: E represents the energy consumption (unit: kilowatt-hour, kWh), T represents the heating temperature (unit: degree Celsius, °C), t represents the heating time (unit: hour, h), and α and β are constants used to adjust the scale of energy consumption calculation and can be obtained by fitting experimental data. Assume that in a certain investment casting process, for every 10°C increase in the heating temperature, the energy consumption increases by 5 kWh / h (i.e., α = 0.5 kWh / °C·h); the basic energy consumption (i.e., the energy consumption that exists even without heating, such as equipment standby energy consumption) is 2 kWh (i.e., β = 2 kWh). If the heating temperature is 1500°C and the heating time is 4 hours, then the energy consumption is: E = 0.5×1500×4 + 2 = 3002 kWh.

[0060] The balance adaptation function needs to comprehensively consider factors of both quality and energy consumption. Assume there is a quality evaluation function Q, which represents the quality of the casting (such as porosity, uniformity of shell film thickness, etc., and can be represented by a comprehensive index, with a value range between 0 and 1, where 1 represents the best quality). Then, the balance adaptation function F can be expressed as: ; or, in order to compare energy consumption and quality on the same magnitude scale, the energy consumption can be normalized to obtain an energy consumption penalty term P E , and then it is combined with the quality evaluation function: ; ; where, and are weight coefficients used to adjust the relative importance of quality and energy consumption in the balance adaptation function; and are respectively the minimum and maximum values of the energy consumption for normalization. Assume the following data is obtained in a certain investment casting project: the value of the quality evaluation function Q is 0.85 (indicating good casting quality); the energy consumption E is 3000 kWh; the minimum value of the energy consumption is 2000 kWh, and the maximum value is 4000 kWh; the weight coefficient = 0.7, = 0.3 (indicating that more importance is attached to quality, but energy consumption is also an important consideration factor). Then the energy consumption penalty term is: ; the balance adaptation function is: F = 0.7×0.85 - 0.3×0.5 = 0.595 - 0.15 = 0.445. This value can be used to compare the comprehensive performance under different parameter combinations, and the larger the value, the better the comprehensive performance. In the process of parameter directional optimization, select those parameter combinations that maximize the value of the balance adaptation function as the optimal solution.

[0061] The method for directional optimization of investment casting parameters provided by the embodiment of the present invention has at least the following technical effects:

[0062] 1. By configuring the directional optimization objectives and clearly distinguishing the main optimization objectives, auxiliary optimization objectives, and maintenance objectives, the comprehensive and precise optimization of the quality of investment casting workpieces is achieved. This multi-objective optimization strategy not only focuses on key quality indicators such as porosity and shell film thickness uniformity but also considers potential problems such as casting shrinkage rate and thermal stress cracks, thus ensuring the comprehensiveness and practicality of the optimization results. Through the calculation of sensitivity coefficients, the key optimization parameters that have the greatest impact on the optimization objectives can be accurately identified, providing a clear direction and focus for subsequent parameter directional optimization and improving the optimization efficiency.

[0063] 2. In the process of parameter directional optimization, an iterative update strategy is adopted. By establishing an iterative trajectory, configuring an iterative evaluation interval, and generating evaluation classifications, the real-time monitoring and intelligent management of the dynamic changes of the solution set are realized. This iterative update method can gradually approach the optimal solution, improving the accuracy and reliability of the optimization results. And the search self-optimization management strategy differentially processes the solution set according to the evaluation classifications. The solutions within the excellent solution evaluation classification are fine-tuned and iteratively updated, the solutions in the exploration evaluation classification are mixedly explored and iteratively updated, and the solutions in the inferior solution evaluation classification are configured with random factors for iterative update. This strategy can make full use of the information of the solution set, improve the search efficiency, and avoid falling into local optimal solutions.

[0064] 3. An energy consumption evaluation function is introduced and combined with the quality evaluation function to establish a balance adaptation function. This balance optimization strategy can effectively control energy consumption while ensuring the quality of castings, achieving a win-win situation for quality and energy consumption. Through the screening of the optimization scheme based on the balance adaptation function, the parameter directional optimization results that meet both quality requirements and low energy consumption can be output, providing strong support for the sustainable development of the investment casting industry.

[0065] Embodiment 2:

[0066] As Figure 2 shown, based on the same inventive concept as the method for directional optimization of investment casting parameters provided in Embodiment 1, the embodiment of the present invention further provides an investment casting parameter directional optimization system, and the system includes:

[0067] A parameter acquisition module 11, configured to acquire the current parameter set of investment casting and establish a quality monitoring database of investment casting workpieces mapped to the current parameter set. Among them, the monitoring indicators of the quality monitoring database include porosity, pore distribution, pore size, shell film thickness distribution, thickness standard deviation, shrinkage rate distribution, crack morphology, and crack size.

[0068] The target configuration module 12 is used to configure the directional optimization targets according to the quality monitoring database. The directional optimization targets include pore optimization, shell film thickness uniformity optimization, casting shrinkage rate optimization, and thermal stress crack optimization.

[0069] The classification identification module 13 is used to determine the target classification identification in the directional optimization targets. The target classification identification includes the main optimization target, the auxiliary optimization target, and the maintenance target.

[0070] The impact analysis module 14 is used to perform the impact analysis of the directional optimization target of the key optimization parameters after selecting the key optimization parameters by using the main optimization target and the auxiliary optimization target.

[0071] The directional optimization module 15 is used to establish parameter optimization constraints according to the results of the directional target optimization impact analysis, perform parameter directional optimization, and complete the directional optimization of the investment casting parameters by using the results of the parameter directional optimization.

[0072] Furthermore, the impact analysis module 14 is also used to perform the following steps:

[0073] Obtain the set of adjustable parameters of the investment casting; perform a quantitative mapping of the influence degree of the set of adjustable parameters on the main optimization target and the auxiliary optimization target; construct a target impact matrix for all the optimization targets in the directional optimization target, where the target impact matrix characterizes the mutual relationship between different optimization targets, and the mutual relationship includes a positive promotion relationship and a negative conflict relationship; calculate the sensitivity coefficient of the set of adjustable parameters according to the quantitative mapping of the influence degree and the target impact matrix; establish the results of the directional target optimization impact analysis according to the calculation results of the sensitivity coefficient.

[0074] Furthermore, the directional optimization module 15 is also used to perform the following steps:

[0075] After establishing the control interval of the parameters, create an initial solution set based on the current parameter set; after performing the solution fitness evaluation within the initial solution set, establish the optimization direction and the optimization step size through the parameter optimization constraints and the fitness evaluation results; use the optimization direction and the optimization step size to iteratively update the initial solution set; complete the parameter directional optimization according to the iterative update results.

[0076] Furthermore, the directional optimization module 15 is also used to perform the following steps:

[0077] Establish an iterative trajectory for each solution, and identify the iterative trajectory through the solution fitness value of each round of iteration; configure an iterative evaluation interval, identify the update status of the iterative trajectory within the iterative evaluation interval, and generate an evaluation classification, where the evaluation classification includes an optimal solution evaluation classification, an exploration evaluation classification, and a suboptimal solution evaluation classification; perform self-optimization management of the iterative update search according to the evaluation classification.

[0078] Furthermore, the orientation optimization module 15 is further configured to perform the following steps:

[0079] Configure a local proxy model in the optimal solution evaluation and classification, use the local proxy model to predict the improvement trend, and generate a first reference optimization direction; configure a penalty optimization recognition layer in the inferior solution evaluation and classification, use the penalty optimization recognition layer to identify the wrong improvement direction, and establish a window improvement taboo; perform fine-tuning iterative update of the solutions within the optimal solution evaluation and classification with the first reference optimization direction and the window improvement taboo, perform hybrid exploration iterative update of the exploration evaluation and classification with the first reference optimization direction and the window improvement taboo, and configure a random factor to perform iterative update of the solutions within the inferior solution evaluation and classification.

[0080] Furthermore, the orientation optimization module 15 is further configured to perform the following steps:

[0081] Establish an energy consumption evaluation function for the parameters; establish a balance adaptation function based on the energy consumption evaluation function and the quality evaluation function; perform screening of the optimization scheme for parameter orientation optimization based on the balance adaptation function, and output the screening result of the optimization scheme as the parameter orientation optimization result.

[0082] Through the foregoing detailed description of a method for directional optimization of investment casting parameters in this specification, those skilled in the art can clearly know a system for directional optimization of investment casting parameters in this embodiment. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For related parts, reference may be made to the description in the method section.

[0083] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for directional optimization of investment casting parameters, characterized in that: The method comprises: Obtaining a current parameter set for investment casting and establishing a quality monitoring database for investment casting workpieces mapped to the current parameter set; Configuring directional optimization targets according to the quality monitoring database, wherein the directional optimization targets include pore optimization, shell film thickness uniformity optimization, casting shrinkage optimization, and thermal stress crack optimization; Determine a target classification identifier in the directional optimization target, wherein the target classification identifier includes a primary optimization target, an auxiliary optimization target, and a maintained target; After selecting key optimization parameters using the main optimization objective and the auxiliary optimization objective, performing directional optimization objective impact analysis of the key optimization parameters; After establishing the parameter optimization constraints according to the results of the directional target optimization impact analysis, the parameter directional optimization is performed, and the directional optimization of the investment casting parameters is completed using the results of the parameter directional optimization; Wherein, after the key optimization parameters are selected by using the main optimization objective and the auxiliary optimization objective, a directional optimization objective impact analysis of the key optimization parameters is performed, including: Get the set of adjustable parameters for investment casting; Performing quantitative mapping of the influence of the adjustable parameter set on the main optimization objective and the auxiliary optimization objective; Constructing a target influence matrix of all optimization targets in the directional optimization target, wherein the target influence matrix represents the mutual relationship between different optimization targets, and the mutual relationship includes a positive promotion relationship and a negative conflict relationship; Calculate the sensitivity coefficients of the adjustable parameter set based on the impact degree quantification mapping and the target impact matrix; Establish the directional target optimization impact analysis results based on the sensitivity coefficient calculation results; The execution parameter directional optimization includes: After establishing the control interval of the parameters, create an initial solution set based on the current parameter set; After executing the fitness evaluation of the solutions in the initial solution set, the optimization direction and optimization step size are established through the parameter optimization constraints and the fitness evaluation results; Iteratively updating the initial solution set using the optimization direction and the optimization step size; Complete parameter directional optimization according to the iterative update results; The iterative updating of the initial solution set using the optimization direction and the optimization step size includes: Establish an iteration trajectory for each solution, and identify the iteration trajectory through the solution fitness value of each round of iteration; Configure an iterative evaluation interval, perform update state identification of the iterative trajectory in the iterative evaluation interval, and generate an evaluation classification, wherein the evaluation classification includes an optimal solution evaluation classification, an exploration evaluation classification, and an inferior solution evaluation classification; Search self-optimization management that performs iterative updates based on the evaluation classification; The search self-optimization management that is iteratively updated according to the evaluation classification includes: In the optimal solution evaluation classification, a local proxy model is configured, and improvement trend prediction is performed using the local proxy model to generate a first reference optimization direction; A penalty optimization identification layer is configured in the inferior solution evaluation classification, and the penalty optimization identification layer is used to identify the wrong improvement direction and establish a window improvement taboo; The first reference optimization direction and window improvement taboo are used to perform iterative updates on fine-tuning of solutions within the superior solution evaluation category. The first reference optimization direction and window improvement taboo are used to perform mixed exploration iterative updates on the exploration evaluation category. Random factors are configured to perform iterative updates on solutions within the inferior solution evaluation category.

2. A method for directional optimization of investment casting parameters according to claim 1, characterized in that: The execution parameter directional optimization further includes: Establish the energy consumption evaluation function of parameters; Establish a balance adaptation function based on the energy consumption evaluation function and the quality evaluation function; Based on the balance adaptation function, the optimization scheme screening of the parameter-oriented optimization is performed, and the optimization scheme screening result is output as the parameter-oriented optimization result.

3. A method for directional optimization of investment casting parameters as claimed in claim 1, characterized in that: The monitoring indicators of the quality monitoring database include porosity, pore distribution, pore size, shell film thickness distribution, thickness standard deviation, shrinkage distribution, crack morphology, and crack size.

4. An investment casting parameter directional optimization system, characterized in that: A method for implementing a directional optimization method for investment casting parameters according to any one of claims 1 to 3, the system comprising: A parameter acquisition module, used to acquire a current parameter set of investment casting and establish a quality monitoring database of investment casting workpieces mapped with the current parameter set; A target configuration module, used to configure directional optimization targets according to the quality monitoring database, wherein the directional optimization targets include pore optimization, shell film thickness uniformity optimization, casting shrinkage optimization, and thermal stress crack optimization; A classification identification module, used to determine the target classification identification in the directional optimization target, wherein the target classification identification includes a main optimization target, an auxiliary optimization target and a maintained target; The impact analysis module is used to select key points using the main optimization target and the auxiliary optimization target. After the key optimization parameters are determined, the directional optimization target impact analysis of the key optimization parameters is performed; The directional optimization module is used to establish parameter optimization constraints according to the results of directional target optimization impact analysis, perform parameter directional optimization, and use the parameter directional optimization results to complete the directional optimization of investment casting parameters.

Images