Metal semi-solid pulping process parameter optimization method
By obtaining and processing the current parameters and finished product profiles of the metal semi-solid pulping process, calculating the weight of historical parameters and building a control model, the control error problem in pulping process parameter optimization is solved, and the stability and consistency of production are improved , achieving more efficient resource utilization.
Patent Information
- Application Number
- CN202411094461.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-22
AI Technical Summary
The prior art lacks the optimization of metal semi-solid pulping process parameters, resulting in control errors and lack of hierarchy and hysteresis compensation.
By obtaining the current process parameters and finished product profile, pre-processing and feature quantity extraction, calculating the weights of historical parameters, setting first- and second-level control parameters, building a control model, using the particle swarm algorithm to update the parameters, and optimizing the process parameters.
Improves the stability and consistency of production, enhances the accuracy of control and management, reduces waste and costs, and improves resource utilization.
Smart Images

Figure CN119007892A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of metal semi-solid pulping, and in particular to a method for optimizing process parameters of metal semi-solid pulping. Background Art
[0002] In recent years, semi-solid thixoforming technology has received widespread attention. Semi-solid thixoforming processing technology utilizes the thixotropic fluidity of alloys or metal-based composite materials after being kept at semi-solid temperature for a certain period of time. It processes parts with complex shapes and high mechanical properties by forging, extrusion, etc. The heating and conveying process is relatively simple and easy to achieve mass production.
[0003] At present, a semi-solid extrusion die-casting method is disclosed in a Chinese invention patent with publication number CN 105127392 B. By reasonably controlling the extrusion speed and the temperature of the semi-solid slurry, the blistering problem of the extrusion die-casting product after heat treatment can be solved, so that the qualified rate of the extrusion die-casting product after heat treatment is above 95%, and the mechanical properties of the extrusion die-casting product after heat treatment can be effectively improved. However, the relevant technology does not optimize the key parameters of slurry making, lacks the hierarchy of optimization, does not compensate for the hysteresis of the parameters, and is prone to control errors. Summary of the invention
[0004] The technical problem solved by the present invention is that the relevant technology does not optimize the key parameters of pulping, lacks the optimization hierarchy, does not compensate for the hysteresis of the parameters, and is prone to control errors.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, a method for optimizing process parameters of metal semi-solid pulping comprises the following steps:
[0006] Step S1, obtaining current process related parameters and current process finished product profile;
[0007] Step S2, preprocessing the cross-sectional view of the current process product, extracting feature quantities of the preprocessed cross-sectional view of the current process product, and determining defects of the current process product according to the feature quantities;
[0008] Step S3, obtaining historical process-related parameters and corresponding historical defects, calculating the weights of the historical process-related parameters in the corresponding historical defects, setting the historical process-related parameter corresponding to the weight with the maximum value as the primary control parameter, and setting the remaining historical process-related parameters as the secondary control parameters;
[0009] Step S4, setting the control rules of the primary control parameters, and updating the coefficients of the control rules, constructing a primary control model, obtaining updated primary control parameters, and setting the remaining historical process-related parameters corresponding to the updated primary control parameters as updated secondary control parameters.
[0010] As a preferred solution of the method for optimizing process parameters of metal semi-solid pulping according to the present invention, step S1 includes the following sub-steps:
[0011] Step S11, calling a pulping database, inputting a molten metal model into the pulping database, and matching process parameters corresponding to the molten metal model and a corresponding process product profile;
[0012] Step S12, setting the process parameters corresponding to the molten metal model as current process parameters, setting the cross-sectional view of the process product corresponding to the molten metal model as the cross-sectional view of the current process product, and the current process-related parameters include injection speed, pouring temperature, mold preheating temperature and holding time.
[0013] As a preferred solution of the method for optimizing process parameters of metal semi-solid pulping according to the present invention, step S2 includes the following sub-steps:
[0014] Step S21, preprocessing the current process finished product profile, wherein the preprocessing includes equalization processing and filtering processing;
[0015] Step S22, extracting characteristic quantities of the cross-sectional view of the current process product after pretreatment, and judging defects of the current process product according to the characteristic quantities, wherein the defects include pores, bubbles, segregation, uneven grains, oversized grains and uneven precipitated phases.
[0016] As a preferred solution of the method for optimizing process parameters of metal semi-solid pulping according to the present invention, the judgment logic of the defects of the finished product of the current process includes:
[0017] Obtain historical defects and historical process profiles corresponding to the historical defects, extract feature quantities of the historical process profiles corresponding to the historical defects, calculate the similarity between the feature quantities of the current process finished product profile and the feature quantities of the historical process profiles, wherein the similarity is calculated according to the cosine similarity formula, and set the historical defect corresponding to the similarity with the largest value as the defect of the current process finished product.
[0018] As a preferred solution of the method for optimizing process parameters of metal semi-solid pulping according to the present invention, step S3 includes the following sub-steps:
[0019] Step S31, obtaining historical process related parameters and corresponding historical defects;
[0020] Step S32, taking the corresponding historical defects as dependent variables and the historical process parameters as independent variables, performing a multivariate regression analysis, constructing a weight analysis model, and taking the coefficient corresponding to the dependent variable as the weight of the dependent variable;
[0021] Step S33, traversing the weights of the dependent variables, setting the historical process-related parameters corresponding to the weights with the maximum values as the primary control parameters, and setting the remaining historical process-related parameters as the secondary control parameters.
[0022] As a preferred solution of the method for optimizing process parameters of metal semi-solid pulping described in the present invention, the calculation expression of the weight analysis model is:
[0023]
[0024] Where Q is the corresponding historical defect, n is the number of historical process parameters, C i is the weight of the i-th historical process parameter in the corresponding historical defect, x i is the i-th historical process parameter.
[0025] As a preferred solution of the method for optimizing process parameters of metal semi-solid pulping according to the present invention, step S4 includes the following sub-steps:
[0026] Step S41, draw a primary control parameter curve, calculate the difference between adjacent primary control parameters in the curve, and calculate the rate of change of the difference, build a primary control model, set the difference between adjacent primary control parameters as a fuzzy value E, set the rate of change of the difference as a fuzzy value EC, set the membership of the fuzzy value E and the fuzzy value EC in each fuzzy set, set the fuzzy domain of the proportional coefficient, the integral coefficient and the differential coefficient, and set the fuzzy subset, the fuzzy subsets respectively include negative large, negative medium, negative small, zero, positive small, positive medium and positive large, the primary control parameter is the pouring temperature, and the secondary control parameters are the injection speed, the mold preheating temperature and the holding time;
[0027] Step S42, updating the proportional coefficient, integral coefficient and differential coefficient according to the particle swarm algorithm, constructing a primary control model, and obtaining updated primary control parameters;
[0028] Step S43, setting the remaining historical process-related parameters corresponding to the updated primary control parameters as updated secondary control parameters.
[0029] As a preferred solution of the method for optimizing process parameters of metal semi-solid pulping described in the present invention, the updating logic of the proportional coefficient, the integral coefficient and the differential coefficient includes:
[0030] The number of initial population particles, the number of iterations, the inertia weight and the acceleration coefficient are set, the position and velocity of each particle are randomly initialized, the position and velocity of the particle are used as the input of the primary control model, the input of the primary control model is run, and the fitness evaluation value of the particle is obtained;
[0031] The position corresponding to the optimal particle fitness value is obtained as the optimal position, and the proportional coefficient, integral coefficient and differential coefficient are updated cyclically. When the optimal particle fitness value reaches the first fitness threshold or reaches the number of iterations, the calculation ends.
[0032] In a second aspect, the present invention provides an electronic device comprising a memory, a processor and storage in the memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in any one of the methods described above are executed.
[0033] In a third aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in any one of the methods described above are executed.
[0034] The beneficial effects of the present invention are as follows: by acquiring current process-related parameters and the current process finished product profile, the current production status can be reflected in real time, which is helpful to promptly discover and deal with problems and defects in the production process; by preprocessing the finished product profile and extracting characteristic quantities, it is helpful to accurately evaluate the quality and defects of the current process finished product; by using historical process-related parameters and corresponding historical defects, weights are calculated and primary and secondary control parameters are set to improve production stability and consistency; control rules for primary control parameters are set and coefficients are updated to construct a primary control model, which is beneficial to real-time adjustment of data, improves the foresight and intelligence of evaluation, and is beneficial to optimizing the production process; through real-time feedback and analysis of historical data, the accuracy of control and management is improved, waste and cost are reduced, and resource utilization is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Figure 1 A basic flow chart of a method for optimizing process parameters of metal semi-solid pulping provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.
[0037] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a method for optimizing process parameters of metal semi-solid pulping, comprising the following steps:
[0038] Step S1, obtaining current process related parameters and current process finished product profile;
[0039] Step S2, preprocessing the cross-sectional view of the current process product, extracting feature quantities of the preprocessed cross-sectional view of the current process product, and determining defects of the current process product according to the feature quantities;
[0040] Step S3, obtaining historical process-related parameters and corresponding historical defects, calculating the weights of the historical process-related parameters in the corresponding historical defects, setting the historical process-related parameter corresponding to the weight with the maximum value as the primary control parameter, and setting the remaining historical process-related parameters as the secondary control parameters;
[0041] Step S4, setting the control rules of the primary control parameters, and updating the coefficients of the control rules, constructing a primary control model, obtaining updated primary control parameters, and setting the remaining historical process-related parameters corresponding to the updated primary control parameters as updated secondary control parameters.
[0042] The present invention can reflect the current production status in real time by acquiring current process-related parameters and the current process finished product profile, which is helpful to timely discover and deal with problems and defects in the production process. By preprocessing the finished product profile and extracting characteristic quantities, it is helpful to accurately evaluate the quality and defects of the current process finished product. The historical process-related parameters and the corresponding historical defects are used to calculate weights and set primary and secondary control parameters to improve production stability and consistency. The control rules of the primary control parameters are set and the coefficients are updated to construct a primary control model, which is beneficial to real-time adjustment of data, improves the foresight and intelligence of the evaluation, and is beneficial to optimizing the production process. Through real-time feedback and analysis of historical data, the accuracy of control and management is improved, waste and cost are reduced, and resource utilization is improved.
[0043] The step S1 includes the following sub-steps:
[0044] Step S11, calling a pulping database, inputting a molten metal model into the pulping database, and matching process parameters corresponding to the molten metal model and a corresponding process product profile;
[0045] Step S12, setting the process parameters corresponding to the molten metal model as current process parameters, setting the cross-sectional view of the process product corresponding to the molten metal model as the cross-sectional view of the current process product, and the current process-related parameters include injection speed, pouring temperature, mold preheating temperature and holding time.
[0046] The step S2 includes the following sub-steps:
[0047] Step S21, preprocessing the current process finished product profile, wherein the preprocessing includes equalization processing and filtering processing;
[0048] In a specific implementation, preprocessing the finished product profile and extracting feature quantities can help accurately evaluate the quality and defects of the current process finished product.
[0049] Step S22, extracting characteristic quantities of the cross-sectional view of the current process product after pretreatment, and judging defects of the current process product according to the characteristic quantities, wherein the defects include pores, bubbles, segregation, uneven grains, oversized grains and uneven precipitated phases.
[0050] In specific implementation, by obtaining the current process-related parameters and the current process finished product profile, the current production status can be reflected in real time, which helps to promptly discover and deal with problems and defects in the production process.
[0051] The judgment logic of the defects of the current process product includes:
[0052] Obtain historical defects and historical process profiles corresponding to the historical defects, extract feature quantities of the historical process profiles corresponding to the historical defects, calculate the similarity between the feature quantities of the current process finished product profile and the feature quantities of the historical process profiles, wherein the similarity is calculated according to the cosine similarity formula, and set the historical defect corresponding to the similarity with the largest value as the defect of the current process finished product.
[0053] The step S3 includes the following sub-steps:
[0054] Step S31, obtaining historical process related parameters and corresponding historical defects;
[0055] Step S32, taking the corresponding historical defects as dependent variables and the historical process parameters as independent variables, performing a multivariate regression analysis, constructing a weight analysis model, and taking the coefficient corresponding to the dependent variable as the weight of the dependent variable;
[0056] Step S33, traversing the weights of the dependent variables, setting the historical process-related parameters corresponding to the weights with the maximum values as the primary control parameters, and setting the remaining historical process-related parameters as the secondary control parameters.
[0057] In the specific implementation, by dividing the historical process-related parameters into primary control parameters and secondary control parameters, the parameter optimization is made more hierarchical. At the same time, the optimization efficiency is improved. The historical process-related parameters and the corresponding historical defects are used to calculate the weights and set the primary and secondary control parameters to improve the stability and consistency of production.
[0058] The calculation expression of the weight analysis model is:
[0059]
[0060] Where Q is the corresponding historical defect, n is the number of historical process parameters, C i is the weight of the i-th historical process parameter in the corresponding historical defect, x i is the i-th historical process parameter.
[0061] In specific implementation, through real-time feedback and analysis of historical data, the accuracy of control and management is improved, waste and cost are reduced, and resource utilization is improved.
[0062] The step S4 includes the following sub-steps:
[0063] Step S41, draw a primary control parameter curve, calculate the difference between adjacent primary control parameters in the curve, and calculate the rate of change of the difference, build a primary control model, set the difference between adjacent primary control parameters as a fuzzy value E, set the rate of change of the difference as a fuzzy value EC, set the membership of the fuzzy value E and the fuzzy value EC in each fuzzy set, set the fuzzy domain of the proportional coefficient, the integral coefficient and the differential coefficient, and set the fuzzy subset, the fuzzy subsets respectively include negative large, negative medium, negative small, zero, positive small, positive medium and positive large, the primary control parameter is the pouring temperature, and the secondary control parameters are the injection speed, the mold preheating temperature and the holding time;
[0064] Step S42, updating the proportional coefficient, integral coefficient and differential coefficient according to the particle swarm algorithm, constructing a primary control model, and obtaining updated primary control parameters;
[0065] Step S43, setting the remaining historical process-related parameters corresponding to the updated primary control parameters as updated secondary control parameters.
[0066] The update logic of the proportional coefficient, integral coefficient and differential coefficient includes:
[0067] The number of initial population particles, the number of iterations, the inertia weight and the acceleration coefficient are set, the position and velocity of each particle are randomly initialized, the position and velocity of the particle are used as the input of the primary control model, the input of the primary control model is run, and the fitness evaluation value of the particle is obtained;
[0068] The position corresponding to the optimal particle fitness value is obtained as the optimal position, and the proportional coefficient, integral coefficient and differential coefficient are updated cyclically. When the optimal particle fitness value reaches the first fitness threshold or reaches the number of iterations, the calculation ends.
[0069] In the specific implementation, the control rules of the first-level control parameters are set and the coefficients are updated to build a first-level control model, which is conducive to the real-time adjustment of data, improves the foresight and intelligence of the evaluation, and is conducive to optimizing the production process.
[0070] The present invention can reflect the current production status in real time by acquiring current process-related parameters and the current process finished product profile, which is helpful to timely discover and deal with problems and defects in the production process. By preprocessing the finished product profile and extracting characteristic quantities, it is helpful to accurately evaluate the quality and defects of the current process finished product. The historical process-related parameters and the corresponding historical defects are used to calculate weights and set primary and secondary control parameters to improve production stability and consistency. The control rules of the primary control parameters are set and the coefficients are updated to construct a primary control model, which is beneficial to real-time adjustment of data, improves the foresight and intelligence of the evaluation, and is beneficial to optimizing the production process. Through real-time feedback and analysis of historical data, the accuracy of control and management is improved, waste and cost are reduced, and resource utilization is improved.
[0071] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 Functions specified in one or more boxes
[0072] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A method for optimizing process parameters of metal semi-solid pulping, characterized in that: The following steps are involved: Step S1, obtaining current process related parameters and current process finished product profile; Step S2, preprocessing the cross-sectional view of the current process product, extracting feature quantities of the preprocessed cross-sectional view of the current process product, and determining defects of the current process product according to the feature quantities; Step S3, obtaining historical process-related parameters and corresponding historical defects, calculating the weights of the historical process-related parameters in the corresponding historical defects, setting the historical process-related parameter corresponding to the weight with the maximum value as the primary control parameter, and setting the remaining historical process-related parameters as the secondary control parameters; Step S4, setting the control rules of the primary control parameters, and updating the coefficients of the control rules, constructing a primary control model, obtaining updated primary control parameters, and setting the remaining historical process-related parameters corresponding to the updated primary control parameters as updated secondary control parameters.
2. A method for optimizing process parameters of metal semi-solid pulping according to claim 1, characterized in that: The step S1 includes the following sub-steps: Step S11, calling a pulping database, inputting a molten metal model into the pulping database, matching process parameters corresponding to the molten metal model and a corresponding process product profile; Step S12, setting the process parameters corresponding to the molten metal model as current process parameters, setting the cross-sectional view of the process product corresponding to the molten metal model as the cross-sectional view of the current process product, and the current process-related parameters include injection speed, pouring temperature, mold preheating temperature and holding time.
3. A method for optimizing process parameters of metal semi-solid pulping according to claim 1, characterized in that: The step S2 includes the following sub-steps: Step S21, preprocessing the current process finished product profile, wherein the preprocessing includes equalization processing and filtering processing; Step S22, extracting characteristic quantities of the cross-sectional view of the current process product after pretreatment, and judging defects of the current process product according to the characteristic quantities, wherein the defects include pores, bubbles, segregation, uneven grains, oversized grains and uneven precipitated phases.
4. A method for optimizing process parameters of metal semi-solid pulping according to claim 3, characterized in that: The judgment logic of the defects of the current process product includes: Obtain historical defects and historical process profiles corresponding to the historical defects, extract feature quantities of the historical process profiles corresponding to the historical defects, calculate the similarity between the feature quantities of the current process finished product profile and the feature quantities of the historical process profiles, wherein the similarity is calculated according to the cosine similarity formula, and set the historical defect corresponding to the similarity with the largest value as the defect of the current process finished product.
5. The method for optimizing process parameters of metal semi-solid pulping according to claim 1, characterized in that: The step S3 includes the following sub-steps: Step S31, obtaining historical process related parameters and corresponding historical defects; Step S32, taking the corresponding historical defects as dependent variables and the historical process parameters as independent variables, performing a multivariate regression analysis, constructing a weight analysis model, and taking the coefficient corresponding to the dependent variable as the weight of the dependent variable; Step S33, traversing the weights of the dependent variables, setting the historical process-related parameters corresponding to the weights with the maximum values as the primary control parameters, and setting the remaining historical process-related parameters as the secondary control parameters.
6. A method for optimizing process parameters of metal semi-solid pulping according to claim 1, characterized in that: The calculation expression of the weight analysis model is: Where Q is the corresponding historical defect, n is the number of historical process parameters, C i is the weight of the i-th historical process parameter in the corresponding historical defect, x i is the i-th historical process parameter.
7. The method for optimizing process parameters of metal semi-solid pulping according to claim 1, characterized in that: The step S4 includes the following sub-steps: Step S41, draw a primary control parameter curve, calculate the difference between adjacent primary control parameters in the curve, and calculate the rate of change of the difference, build a primary control model, set the difference between adjacent primary control parameters as a fuzzy value E, set the rate of change of the difference as a fuzzy value EC, set the membership of the fuzzy value E and the fuzzy value EC in each fuzzy set, set the fuzzy domain of the proportional coefficient, the integral coefficient and the differential coefficient, and set the fuzzy subset, the fuzzy subsets respectively include negative large, negative medium, negative small, zero, positive small, positive medium and positive large, the primary control parameter is the pouring temperature, and the secondary control parameters are the injection speed, the mold preheating temperature and the holding time; Step S42, updating the proportional coefficient, integral coefficient and differential coefficient according to the particle swarm algorithm, constructing a primary control model, and obtaining updated primary control parameters; Step S43, setting the remaining historical process-related parameters corresponding to the updated primary control parameters as updated secondary control parameters.
8. A method for optimizing process parameters of metal semi-solid pulping according to claim 7, characterized in that: The update logic of the proportional coefficient, integral coefficient and differential coefficient includes: The number of initial population particles, the number of iterations, the inertia weight and the acceleration coefficient are set, the position and velocity of each particle are randomly initialized, the position and velocity of the particle are used as the input of the primary control model, the input of the primary control model is run, and the fitness evaluation value of the particle is obtained; The position corresponding to the optimal particle fitness value is obtained as the optimal position, and the proportional coefficient, integral coefficient and differential coefficient are updated cyclically. When the optimal particle fitness value reaches the first fitness threshold or reaches the number of iterations, the calculation ends.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for optimizing process parameters of metal semi-solid pulping according to any one of claims 1 to 8 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for optimizing process parameters of metal semi-solid pulping according to any one of claims 1 to 8 is implemented.
Citation Information
Cited By
Plastic part screen printing control method and system
CN119323698A
A plastic part screen printing control method and system
CN119323698B
Stamping production line dynamic step planning system oriented to multi-objective optimization
CN122311803A
