Optimization method for high performance metallic glass mold based on multi-objective optimization algorithm

By classifying and marking the key positions of metal glass molds and data analysis, using multi-objective optimization algorithms and acoustic wave conduction velocity parameters, dynamically adjusting the contact time, temperature, pressure and other parameters, the problem of inconsistent finished product quality in the existing technology is solved, significantly Improves mold optimization efficiency and stability of finished product quality.

CN118797847BActive Publication Date: 2024-11-15CHANGSHU INSTITUTE OF TECHNOLOGY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411266139.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-11-15
Estimated Expiration
2044-09-11

AI Technical Summary

Technical Problem

The existing technology has failed to effectively combine multi-objective optimization algorithm to systematically optimize the key positions of metal glass molds, dynamically adjust the key parameters of contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation speed, resulting in the finished product Inconsistent quality.

Method used

By classifying and marking the preformed molds and data storage, collecting and analyzing the working data at key positions, building evaluation coefficients, and dynamically adjusting using multi-objective optimization algorithms, combining the acoustic wave conduction velocity parameters to generate calibration coefficients, and setting the judgment of evaluation coefficients Thresholds are fine-tuned to optimize vertical load.

Benefits of technology

Accurate control of contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation speed is achieved, and the consistency and stability of mold optimization efficiency and finished product quality are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118797847B_ABST
    Figure CN118797847B_ABST
Patent Text Reader

Abstract

The present invention provides a high-performance metallic glass mold optimization method based on a multi-objective optimization algorithm, and relates to the technical field of mold design. The present invention classifies and marks preformed molds and stores data, collects and analyzes working data at key positions, constructs evaluation coefficients, and uses a multi-objective optimization algorithm for dynamic adjustment, thereby achieving precise control of key parameters such as contact time, contact temperature, contact pressure, vertical load, stress value, and heat dissipation speed, collecting sound wave conduction velocity parameters, generating calibration coefficients for correcting the evaluation coefficients, and fine-tuning the vertical load by setting a judgment threshold of the evaluation coefficient, thereby improving the optimization efficiency of the mold and significantly improving the consistency and stability of the quality of the finished product.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of mold design, and in particular to a high-performance metallic glass mold optimization method based on a multi-objective optimization algorithm. Background Art

[0002] With the increasing demand for high-performance materials in modern industry, metallic glass molds play an important role in the molding process of glass products, especially in the production of glass products with complex shapes and high precision requirements. However, the traditional metallic glass mold design and manufacturing methods have some limitations, which are mainly reflected in the optimization efficiency of the mold and the consistency of the finished product quality. In recent years, with the advancement of computing technology and optimization algorithms, multi-objective optimization algorithms have gradually been introduced into the design and optimization of metallic glass molds, aiming to improve the performance and manufacturing efficiency of the molds.

[0003] In the prior art, the publication number is CN117556677B, and the name is a profile mold optimization method and system based on a multi-objective optimization algorithm. The method includes the following steps: obtaining mold structure parameters of a target mold to be optimized, and profile parameters of a target profile produced by using the target mold; determining and optimizing a thermal deformation constitutive model of the target profile based on the profile parameters; performing profile forming finite element simulation on the target mold according to the thermal deformation constitutive model, and determining multiple optimization variable indicators and optimization targets; obtaining the influence relationship between the mold structure parameters and multiple optimization variable indicators through response surface analysis, and constructing a parameter relationship model between the mold structure parameters and multiple optimization variable indicators; performing multi-objective optimization on the parameter relationship model based on the optimization target and using the NSGA2 algorithm to obtain an optimization final solution that achieves all optimization targets; optimizing and adjusting the mold structure parameters through optimizing the final solution;

[0004] However, the existing technology still has major defects, such as: the existing technology does not mention how to effectively combine the multi-objective optimization algorithm, systematically optimize the working data of the key positions of the metallic glass mold, and use the multi-objective optimization algorithm to perform dynamic adjustments, so as to achieve precise control of the key parameters of contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation speed, which is an urgent problem to be solved;

[0005] The above information disclosed in the above Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a high-performance metallic glass mold optimization method based on a multi-objective optimization algorithm to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A high-performance metallic glass mold optimization method based on a multi-objective optimization algorithm includes the following specific steps:

[0009] Step S1: obtaining a target mold to be optimized, the target mold including a preformed mold for forming glass products, obtaining design requirements of the preformed mold in advance, and classifying and marking key positions of the preformed mold based on the design requirements to form a classification set {a, b, c, d}, wherein a, b, c, d represent a cavity wall contact point, a cavity volume measurement point, a cavity bottom vertical load measurement point, and a cavity heat dissipation point, respectively, and at the same time, storing the working data of each key position in the classification set {a, b, c, d} to form a storage database;

[0010] Step S2: collecting contact time, contact temperature and contact pressure data of the cavity wall contact point, determining first target value ranges corresponding to the contact time, contact temperature and contact pressure respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding first target value ranges to construct a first target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the cavity wall contact point and the first target value range;

[0011] Step S3: Collecting the actual cavity volume and glass liquid weight data at the cavity volume measurement point, determining the second target value ranges of the actual cavity volume and glass liquid weight respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding second target value ranges to construct a second target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected at the cavity volume measurement point and the second target value range;

[0012] Step S4: collecting vertical load and stress value data of the vertical load measurement point at the bottom of the mold cavity, determining the third target value ranges corresponding to the vertical load and stress value respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding third target value ranges to construct a third target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the vertical load measurement point at the bottom of the mold cavity and the third target value range;

[0013] Step S5: collecting heat dissipation speed and temperature uniformity data of the heat dissipation points of the mold cavity, determining fourth target value ranges corresponding to the heat dissipation speed and temperature uniformity respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding fourth target value ranges to construct a fourth target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the heat dissipation points of the mold cavity and the fourth target value range;

[0014] Step S6: respectively collecting the first acoustic wave transmission velocity parameter of the cavity wall contact point and the second acoustic wave transmission velocity parameter of the cavity heat dissipation point, and analyzing and processing the first acoustic wave transmission velocity parameter and the second acoustic wave transmission velocity parameter to generate a calibration coefficient, which is used to correct the first target evaluation coefficient and the fourth target evaluation coefficient respectively;

[0015] Step S7: respectively determining the target values ​​of the third target evaluation coefficient, and the corrected first target evaluation coefficient and the fourth target evaluation coefficient, and inputting the determined target values ​​into the multi-objective optimization algorithm to dynamically adjust the contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation speed of the preforming mold;

[0016] Step S8: Setting a judgment threshold of the second target evaluation coefficient, and only when the second target evaluation coefficient is greater than the set judgment threshold, fine-tuning the vertical load.

[0017] Furthermore, the target values ​​are input into the multi-objective optimization algorithm to dynamically adjust the contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation rate of the preform mold, including:

[0018] 1.1) According to the process requirements and design requirements of the preforming mold, determine the following target values:

[0019] Determine the third target evaluation coefficient The target value is ;

[0020] Determine the corrected first target evaluation coefficient and the fourth objective evaluation coefficient The target values ​​of and ;

[0021] 2.1) Contact time Adjustments:

[0022] when Greater than The adjustment strategy is as follows:

[0023] like Greater than 105% multiple value, you need to reduce ;

[0024] like exist If the value is below 105%, it is necessary to maintain Current value;

[0025] The mathematical expression of the adjustment is as follows:

[0026]

[0027] in, is the proportionality constant, , for and The difference, for Adjustment amount;

[0028] 2.2) For contact temperature Adjustments:

[0029] when Greater than The adjustment strategy is as follows:

[0030] like Greater than 107% multiple value, you need to reduce ;

[0031] like exist If the value is below 107%, it is necessary to maintain Current value;

[0032] The mathematical expression of the adjustment is as follows:

[0033]

[0034] in, is the proportionality constant, , for and The difference, for Adjustment amount;

[0035] 2.3) For contact pressure Adjustments:

[0036] when Greater than The adjustment strategy is as follows:

[0037] like Greater than 104% multiple value, you need to reduce ;

[0038] like exist If the value is below 104%, it is necessary to maintain Current value;

[0039] The mathematical expression of the adjustment amount is as follows:

[0040]

[0041] in, is the proportionality constant, , for and The difference, for Adjustment amount;

[0042] 2.4) For vertical load Adjustments:

[0043] when Greater than The adjustment strategy is as follows:

[0044] like Greater than 106% multiple value, you need to reduce ;

[0045] like exist If the value is below 106%, it is necessary to maintain Current value;

[0046] The mathematical expression of the adjustment amount is as follows:

[0047]

[0048] in, is the proportionality constant, , for and The difference, for Adjustment amount;

[0049] 2.5) For stress values Adjustments:

[0050] when Greater than The adjustment strategy is as follows:

[0051] like Greater than 108% multiple value, you need to reduce ;

[0052] like exist If the value is below 108% of the Current value;

[0053] The mathematical expression of the adjustment amount is as follows:

[0054]

[0055] in, is the proportionality constant, , for and The difference, for Adjustment amount;

[0056] 2.6) Regarding heat dissipation speed Adjustments:

[0057] when Greater than The adjustment strategy is as follows:

[0058] like Greater than 109% multiple value, you need to reduce ;

[0059] like exist If the value is below 109% of the Current value;

[0060] The mathematical expression of the adjustment amount is as follows:

[0061]

[0062] in, is the proportionality constant, , for and The difference, for Adjustment amount.

[0063] Furthermore, the second target evaluation coefficient is set The judgment threshold is Q1, and 0.34≤Q1≤0.67, and the reference value of Q1 is set to 0.56. When the vertical load is adjusted, the fine-tuning formula is as follows:

[0064]

[0065] in, is the vertical load adjustment The value after fine-tuning.

[0066] Compared with the prior art, the beneficial effects of the present invention are: by classifying and marking the preforming mold and storing the data, collecting and analyzing the working data of the key positions, constructing the evaluation coefficient, and using the multi-objective optimization algorithm for dynamic adjustment, it is possible to achieve precise control of the key parameters of contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation speed, collect the sound wave conduction velocity parameters, generate the calibration coefficient for correcting the evaluation coefficient, and fine-tune the vertical load by setting the judgment threshold of the evaluation coefficient, thereby improving the optimization efficiency of the mold and significantly improving the consistency and stability of the finished product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0068] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0069] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0070] Embodiment 1

[0071] See also Figure 1 , the present invention provides a technical solution:

[0072] A high-performance metallic glass mold optimization method based on a multi-objective optimization algorithm includes the following specific steps:

[0073] Step S1: obtaining a target mold to be optimized, the target mold including a preforming mold and a forming mold for forming glass products, obtaining design requirements of the preforming mold in advance, and classifying and marking key positions of the preforming mold based on the design requirements to form a classification set {a, b, c, d}, wherein a, b, c, d represent a cavity wall contact point, a cavity volume measurement point, a cavity bottom vertical load measurement point, and a cavity heat dissipation point, respectively, and at the same time, storing the working data of each key position in the classification set {a, b, c, d} to form a storage database;

[0074] Step S2: collecting contact time, contact temperature and contact pressure data of the cavity wall contact point, determining first target value ranges corresponding to the contact time, contact temperature and contact pressure respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding first target value ranges to construct a first target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the cavity wall contact point and the first target value range;

[0075] Step S3: Collecting the actual cavity volume and glass liquid weight data at the cavity volume measurement point, determining the second target value ranges of the actual cavity volume and glass liquid weight respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding second target value ranges to construct a second target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected at the cavity volume measurement point and the second target value range;

[0076] Step S4: collecting vertical load and stress value data of the vertical load measurement point at the bottom of the mold cavity, determining the third target value ranges corresponding to the vertical load and stress value respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding third target value ranges to construct a third target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the vertical load measurement point at the bottom of the mold cavity and the third target value range;

[0077] Step S5: collecting heat dissipation speed and temperature uniformity data of the heat dissipation points of the mold cavity, determining fourth target value ranges corresponding to the heat dissipation speed and temperature uniformity respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding fourth target value ranges to construct a fourth target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the heat dissipation points of the mold cavity and the fourth target value range;

[0078] Step S6: respectively collecting the first acoustic wave transmission velocity parameter of the cavity wall contact point and the second acoustic wave transmission velocity parameter of the cavity heat dissipation point, and analyzing and processing the first acoustic wave transmission velocity parameter and the second acoustic wave transmission velocity parameter to generate a calibration coefficient, which is used to correct the first target evaluation coefficient and the fourth target evaluation coefficient respectively;

[0079] Step S7: respectively determining the target values ​​of the second target evaluation coefficient, the third target evaluation coefficient, and the corrected first target evaluation coefficient and the fourth target evaluation coefficient, and inputting the target value of each evaluation coefficient into the multi-objective optimization algorithm to dynamically adjust the contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation speed of the preforming mold;

[0080] Step S8: Setting a judgment threshold of the second target evaluation coefficient, and only when the second target evaluation coefficient is greater than the set judgment threshold, fine-tuning the vertical load.

[0081] Further explanation: the design requirements for preforming molds are obtained in advance, including:

[0082] According to the design requirements of mold material, mold size and temperature tolerance range, select molds that meet the specifications of target glass products from the existing mold database;

[0083] Record the basic information of the target mold, including mold material, mold size, glass product specifications and molding process requirements;

[0084] After obtaining the target mold, the design requirements of the preforming mold are specifically determined. The design requirements include the following aspects:

[0085] 1) The contact requirements of the glass bubble; according to the glass product forming process, the contact time, contact temperature and contact pressure requirements of the glass bubble in the preform mold are determined;

[0086] 2) Volume and weight requirements of the preform mold; the actual volume of the preform mold cavity and the weight of the glass liquid are calculated based on the material properties and the volume of the glass liquid;

[0087] 3) Requirements for vertical load and stress value of the mold; analyze the vertical load and stress value that the mold needs to bear during the molding process to ensure that the stress of each part of the mold does not exceed the yield strength of the material to prevent plastic deformation;

[0088] 4) Requirements for heat dissipation speed and temperature uniformity of the mold; Determine the heat dissipation speed and temperature uniformity of the mold to ensure uniform heat dissipation and prevent thermal stress concentration;

[0089] Classification marking is performed at key locations of the preform mold, including:

[0090] According to the obtained design requirements, classification marks are made at the key positions of the preforming mold to form a classification set {a, b, c, d}, which is described as follows:

[0091] a is a cavity wall contact point, and several positions in the cavity wall contact point are marked to form a first number set {a1, a2, ..., an}, where an represents the number index of the an-th contact position in the first number set, and an represents the total number of contact positions, and ai∈{a1, a2, ..., an} is set, where ai represents the number index of the ai-th contact position in the first number set;

[0092] b is a cavity volume measurement point, and several positions in the cavity volume measurement point are marked to form a second numbering set {b1, b2, ..., bm}, where bm represents the numbering index of the volume measurement position at the bmth position in the second numbering set, and bm represents the total number of volume measurement positions, and bj∈{b1, b2, ..., bm} is set, where bj represents the numbering index of the volume measurement position at the bjth position in the second numbering set;

[0093] c is a vertical load measurement point at the bottom of the mold cavity, and several positions in the measurement points at the bottom of the mold cavity are marked to form a third numbering set {c1, c2, ..., ck}, where ck represents the numbering index of the ckth measurement position in the third numbering set, and ck represents the total number of measurement positions, and cr∈{c1, c2, ..., ck} is set, where cr represents the numbering index of the crth measurement position in the third numbering set;

[0094] d is a heat dissipation point of the mold cavity, and several positions in the heat dissipation points of the mold cavity are marked to form a fourth numbering set {d1, d2, ..., du}, where du represents the numbering index of the heat dissipation position at the duth position in the fourth numbering set, and du represents the total number of heat dissipation positions, and dh∈{d1, d2, ..., du} is set, where dh represents the numbering index of the heat dissipation position at the dhth position in the fourth numbering set;

[0095] The working data of each key position in the classification set {a, b, c, d} is stored to form a storage database. The specific stored data includes:

[0096] The working data of each key position marked above is collected and stored to form a systematic storage database. The specific stored data includes:

[0097] Contact time, contact temperature and contact pressure of the cavity wall contact point;

[0098] The actual volume of the mold cavity and the weight of the glass liquid at the mold cavity volume measurement point;

[0099] Vertical load and stress values ​​at the measuring point at the bottom of the cavity;

[0100] The heat dissipation rate and temperature uniformity of the heat dissipation points in the mold cavity.

[0101] The specific implementation steps of the storage database are as follows:

[0102] During the operation of the mold, sensors and data acquisition systems are used to collect data at key locations in real time;

[0103] The collected data is transmitted to the central database through the data transmission system;

[0104] Classify and store the collected data to form a complete storage database;

[0105] Establish a data index system to facilitate subsequent data analysis and optimization.

[0106] Further explanation: determining the value range of the first target and constructing the first target evaluation coefficient specifically include:

[0107] In the first number set {a1, a2, ..., an}, the contact time, contact temperature and contact pressure at ai are marked as JCt ai , JCw ai , JTl ai ;

[0108] A sensor is installed at each contact position to collect the contact time (JCt) of the aith contact position in real time. ai )、Contact temperature(JCw ai ) and contact pressure (JTl ai )data;

[0109] The collected data is transmitted to the central database through the data transmission system to ensure the real-time and accuracy of the data;

[0110] Regularly calibrate the sensor to ensure the reliability of the collected data;

[0111] According to the requirements of glass product molding process, referring to the existing process data and experimental data, the first target value range of contact time is determined as follows: In this embodiment, the value range is [0.5-2], unit (seconds), and Take the average of the two end points , and As the contact time target value of the ai-th contact position;

[0112] According to the physical properties of glass materials and the molding temperature requirements, the first target range of the contact temperature is determined as follows: In this embodiment, the value range is [800-1000], the unit is (degrees Celsius), and Take the average of the two end points , and As the contact temperature target value of the ai-th contact position;

[0113] According to the molding pressure and mold material characteristics, the first target value range of the contact pressure is determined as follows: In this embodiment, the value range is [50-100], the unit is (N / cm²), and Take the average of the two end points , and As the contact pressure target value at the ai-th contact position;

[0114] , and The expert group made adjustments based on experimental data and will not elaborate on this;

[0115] Calculate the contact time (JCt) of the contact position ai ai )、Contact temperature(JCw ai ) and contact pressure (JTl ai ) and the average deviation of the first target value range. The calculation formula of the average deviation is as follows:

[0116]

[0117] in, , , denote the average deviations of contact time, contact temperature and contact pressure at the contact positions in the first numbered set {a1, a2, …, an} respectively;

[0118] According to the above average deviation, the first target evaluation coefficient is comprehensively defined as , and its calculation formula is:

[0119]

[0120] in, , , They are weight coefficients of contact time, contact temperature and contact pressure, and the weight coefficients are set according to actual process requirements;

[0121]

[0122] limited The value range is (0,1). The closer it is to 0, the smaller the deviation is, and the closer it is to 1, the greater the deviation is.

[0123] The processed data and evaluation coefficients are fed back to the design team and process engineers to provide data support and facilitate optimization and adjustment of molds and processes.

[0124] Further explanation: determining the value range of the second target and constructing the second target evaluation coefficient specifically include:

[0125] In the second number set {b1, b2, ..., bm}, the actual volume of the mold cavity and the weight of the glass liquid at bj are marked as , ;

[0126] A sensor is installed at each measuring position to collect the actual volume of the mold cavity and the weight of the glass liquid at the bjth measuring position in real time;

[0127] The collected data is transmitted to the central database through the data transmission system to ensure the real-time and accuracy of the data;

[0128] Regularly calibrate the sensor to ensure the reliability of the collected data;

[0129] According to the material properties and glass liquid volume requirements, referring to the existing process data and experimental data, the second target value range of the actual cavity volume is determined as follows: , and in Take the average of the two end points , and As the target value of the actual volume of the mold cavity at the bjth measurement position;

[0130] Determine the second target value range of the glass liquid weight , and in Take the average of the two end points , and As the target value of the glass liquid weight at the bjth measuring position;

[0131] and The expert group made adjustments based on experimental data and will not elaborate on this;

[0132] Calculate the average deviation between the actual volume of the mold cavity and the weight of the glass liquid at the bjth measurement position and the second target value range. The calculation formula for the average deviation is as follows:

[0133]

[0134] in, , represent the average values ​​of the deviations of the actual volume of the mold cavity and the weight of the molten glass at the measurement positions in the second numbered set {b1, b2, …, bm} respectively;

[0135] According to the above average deviation, the second target evaluation coefficient is comprehensively defined as , and its calculation formula is:

[0136]

[0137] limited The value range is (0,1). The closer it is to 0, the smaller the deviation is, and the closer it is to 1, the greater the deviation is.

[0138] in, , They are weight coefficients of the actual volume of the mold cavity and the weight of the glass liquid, respectively. The weight coefficients are set according to the actual process requirements.

[0139]

[0140] The processed data and evaluation coefficients are fed back to the design team and process engineers to provide data support and facilitate optimization and adjustment of molds and processes.

[0141] Further explanation: determining the value range of the third target and constructing the third target evaluation coefficient specifically include:

[0142] In the third number set {c1, c2, …, ck}, the vertical load and stress values ​​at cr are marked as , ;

[0143] A sensor is installed at each measuring point to collect the vertical load and stress value data at the cr measuring position in real time;

[0144] The collected data is transmitted to the central database through the data transmission system to ensure the real-time and accuracy of the data;

[0145] Regularly calibrate the sensor to ensure the reliability of the collected data;

[0146] Analyze the vertical load and stress value that the mold needs to bear during the molding process, and determine the third target value range of the vertical load as , and in Take the average of the two end points , and As the vertical load target value at the crth measuring position;

[0147] Determine the third target range of stress value: , and in Take the average of the two end points , and As the target stress value at the crth measuring position;

[0148] and The expert group made adjustments based on experimental data and will not elaborate on this;

[0149] Calculate the average deviation between the vertical load and stress values ​​at the cr measurement position and the third target value range. The calculation formula for the average deviation is as follows:

[0150]

[0151] in, , represent the average deviations of the vertical load and stress values ​​at the measurement positions in the third numbered set {c1, c2, …, ck}, respectively;

[0152] According to the above average deviation, the third target evaluation coefficient is comprehensively defined as , and its calculation formula is:

[0153]

[0154] limited The value range is (0,1). The closer it is to 0, the smaller the deviation is, and the closer it is to 1, the greater the deviation is.

[0155] in, , They are weight coefficients of vertical load and stress value respectively, and the weight coefficients are set according to the actual process requirements;

[0156]

[0157] The processed data and evaluation coefficients are fed back to the design team and process engineers to provide data support and facilitate optimization and adjustment of molds and processes.

[0158] Further explanation: determining the value range of the fourth objective and constructing the fourth objective evaluation coefficient specifically include:

[0159] In the fourth numbered set {d1, d2, ..., du}, the heat dissipation rate and temperature uniformity at dh are marked as , ;

[0160] A sensor is installed at each heat dissipation point to collect the heat dissipation speed and temperature uniformity data of the heat dissipation position at the dhth place in real time;

[0161] The collected data is transmitted to the central database through the data transmission system to ensure the real-time and accuracy of the data;

[0162] Regularly calibrate the sensor to ensure the reliability of the collected data;

[0163] The fourth target value range for determining the heat dissipation rate is , and in Take the average of the two end points , and As the heat dissipation speed target value at the heat dissipation position at dh;

[0164] The fourth target value range for determining temperature uniformity is , and in Take the average of the two end points , and As the temperature uniformity target value of the heat dissipation position at dh;

[0165] and The expert group made adjustments based on experimental data and will not elaborate on this;

[0166] Calculate the average deviation between the heat dissipation rate and temperature uniformity at the heat dissipation position dh and the fourth target value range. The calculation formula for the average deviation is as follows:

[0167]

[0168] in, , represent the average values ​​of the deviation of the heat dissipation speed and the temperature uniformity in the heat dissipation position in the fourth numbered set {d1, d2, …, du} respectively;

[0169] According to the above average deviation, the fourth target evaluation coefficient is comprehensively defined as , and its calculation formula is:

[0170]

[0171] limited The value range is (0,1). The closer it is to 0, the smaller the deviation is, and the closer it is to 1, the greater the deviation is.

[0172] in, , They are weight coefficients of heat dissipation speed and temperature uniformity, respectively. The weight coefficients are set according to actual process requirements.

[0173]

[0174] The processed data and evaluation coefficients are fed back to the design team and process engineers to provide data support and facilitate optimization and adjustment of molds and processes.

[0175] Further explanation, in the first number set {a1, a2, ..., an}, the first acoustic wave transmission velocity parameter collected at the cavity wall contact point ai is recorded as SW1ai ;

[0176] The first step of collecting the acoustic wave velocity parameters is as follows:

[0177] Install an acoustic wave sensor at each marked position in the first number set {a1, a2, ..., an}, ensuring that the sensor is in close contact with the surface of the mold cavity wall;

[0178] Start the acoustic wave sensor to collect the first acoustic wave transmission velocity parameters of each marked position, and transmit the data to the central database in real time for storage;

[0179] Regularly calibrate the acoustic wave sensor to ensure the accuracy and consistency of data collection;

[0180] In the fourth numbered set {d1, d2, ..., du}, the second acoustic wave transmission velocity parameter collected at the heat dissipation point dh of the mold cavity is recorded as SW2 dh ;

[0181] The steps for collecting the second acoustic wave velocity parameters are as follows:

[0182] Install an acoustic wave sensor at each marked position in the fourth number set {d1, d2, …, du}, ensuring that the sensor is close to the heat dissipation area of ​​the mold cavity;

[0183] Start the acoustic wave sensor to collect the second acoustic wave transmission velocity parameters of each marked position, and transmit the data to the central database in real time for storage;

[0184] Regularly calibrate the acoustic wave sensor to ensure the accuracy and consistency of data collection;

[0185] According to the storage database and the standard manual referenced by the design requirements, the standard values ​​of the first sound wave conduction velocity parameter and the second sound wave conduction velocity parameter are determined as follows: and , further calculate the calibration coefficients K1 and K4:

[0186]

[0187] Use the calibration coefficients K1 and K4 to calibrate the first target evaluation coefficients respectively and the fourth objective evaluation coefficient , the correction formula is as follows:

[0188]

[0189] in, represents the corrected first objective evaluation coefficient, Represents the fourth objective evaluation coefficient after correction.

[0190] Further, the contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation speed of the preforming mold are dynamically adjusted, specifically including:

[0191] The multi-objective optimization algorithm of this embodiment adopts the non-dominated sorting genetic algorithm II (NSGA-II);

[0192] NSGA-II dynamically adjusts the parameters of the preform mold through the following steps:

[0193] Initialize the population:

[0194] A set of solutions is randomly generated, each solution represents a parameter combination of the preform mold, including contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation rate;

[0195] Calculate fitness:

[0196] Calculate the fitness value of each solution according to a predetermined objective function (in this embodiment, on the basis of maximizing mold performance, respectively determine the target values ​​of the third target evaluation coefficient, and the corrected first target evaluation coefficient and the fourth target evaluation coefficient);

[0197] Non-dominated sorting and congestion calculation:

[0198] Perform non-dominated sorting on the population and divide the solutions into different Pareto fronts;

[0199] Calculate the crowding distance of each solution to maintain the diversity of the population;

[0200] Selection, crossover, and mutation:

[0201] According to the fitness value and crowding distance, excellent solutions are selected for crossover and mutation to generate the next generation population;

[0202] Iterative Optimization:

[0203] Repeat the above steps until the predetermined number of iterations is reached or the stopping condition is met (such as finding a satisfactory Pareto optimal solution set);

[0204] According to the requirements of the above multi-objective optimization algorithm, first determine the third objective evaluation coefficient, and the target values ​​of the corrected first objective evaluation coefficient and the fourth objective evaluation coefficient;

[0205] 1.1) Determine the third target evaluation coefficient according to the process requirements and design requirements of the preforming mold The target value is ;

[0206] Determine the corrected first target evaluation coefficient and the fourth objective evaluation coefficient The target value of and ; These target values ​​can also be determined and adjusted based on experimental data from the expert group. In this embodiment, , and The median or average value of the corresponding value can be used;

[0207] Through the multi-objective optimization algorithm, the contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation rate of the preforming mold are dynamically adjusted to optimize the mold performance;

[0208] Enter the corrected target evaluation coefficient and , and the third objective evaluation coefficient The objective value to multi-objective optimization algorithm;

[0209] 2.1) Contact time Adjustments:

[0210] when Greater than The adjustment strategy is as follows:

[0211] like Greater than 105% multiple value, you need to reduce ;

[0212] like exist If the value is below 105%, it is necessary to maintain Current value;

[0213] The mathematical expression of the adjustment is as follows:

[0214]

[0215] in, is the proportionality constant, , for and The difference, for Adjustment amount, It is determined by the expert group through experimental data and will not be elaborated on here;

[0216] 2.2) For contact temperature Adjustments:

[0217] when Greater than The adjustment strategy is as follows:

[0218] like Greater than 107% multiple value, you need to reduce ;

[0219] like exist If the value is below 107%, it is necessary to maintain Current value;

[0220] The mathematical expression of the adjustment is as follows:

[0221]

[0222] in, is the proportionality constant, , for and The difference, for Adjustment amount, It is determined by the expert group through experimental data and will not be elaborated on here;

[0223] 2.3) For contact pressure Adjustments:

[0224] when Greater than The adjustment strategy is as follows:

[0225] like Greater than 104% multiple value, you need to reduce ;

[0226] like exist If the value is below 104%, it is necessary to maintain Current value;

[0227] The mathematical expression of the adjustment amount is as follows:

[0228]

[0229] in, is the proportionality constant, , for and The difference, for Adjustment amount, It is determined by the expert group through experimental data and will not be elaborated on here;

[0230] 2.4) For vertical load Adjustments:

[0231] when Greater than The adjustment strategy is as follows:

[0232] like Greater than 106% multiple value, you need to reduce ;

[0233] like exist If the value is below 106%, it is necessary to maintain Current value;

[0234] The mathematical expression of the adjustment amount is as follows:

[0235]

[0236] in, is the proportionality constant, , for and The difference, for Adjustment amount, It is determined by the expert group through experimental data and will not be elaborated on here;

[0237] 2.5) For stress values Adjustments:

[0238] when Greater than The adjustment strategy is as follows:

[0239] like Greater than 108% multiple value, you need to reduce ;

[0240] like exist If the Current value;

[0241] The mathematical expression of the adjustment amount is as follows:

[0242]

[0243] in, is the proportionality constant, , for and The difference, for Adjustment amount, It is determined by the expert group through experimental data and will not be elaborated on here;

[0244] 2.6) Regarding heat dissipation speed Adjustments:

[0245] when Greater than The adjustment strategy is as follows:

[0246] like Greater than 109% multiple value, you need to reduce ;

[0247] like exist If the value is below 109% of the Current value;

[0248] The mathematical expression of the adjustment amount is as follows:

[0249]

[0250] in, is the proportionality constant, , for and The difference, for Adjustment amount, It is determined based on experimental data from an expert group and will not be elaborated on here.

[0251] Further explanation: setting a judgment threshold of the second target evaluation coefficient, and only when the second target evaluation coefficient is greater than the set judgment threshold, fine-tuning the vertical load adjustment amount, specifically includes:

[0252] Set the second target evaluation coefficient The judgment threshold is Q1, and 0.34≤Q1≤0.67, (the specific value of Q1 is determined by the expert group through adjustment of experimental data) and the benchmark value of Q1 is set to 0.56. When the vertical load is adjusted, the fine-tuning formula is as follows:

[0253]

[0254] in, is the vertical load adjustment The value after fine-tuning.

[0255] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0256] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0257] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0258] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A high-performance metallic glass mold optimization method based on a multi-objective optimization algorithm, characterized in that: The specific steps include: Step S1: obtaining a target mold to be optimized, the target mold including a preformed mold for forming glass products, obtaining design requirements of the preformed mold in advance, and classifying and marking key positions of the preformed mold based on the design requirements to form a classification set {a, b, c, d}, wherein a, b, c, d represent a cavity wall contact point, a cavity volume measurement point, a cavity bottom vertical load measurement point, and a cavity heat dissipation point, respectively, and at the same time, storing the working data of each key position in the classification set {a, b, c, d} to form a storage database; Step S2: collecting contact time, contact temperature and contact pressure data of the cavity wall contact point, determining first target value ranges corresponding to the contact time, contact temperature and contact pressure respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding first target value ranges to construct a first target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the cavity wall contact point and the first target value range; Step S3: Collecting the actual cavity volume and glass liquid weight data at the cavity volume measurement point, determining the second target value ranges of the actual cavity volume and glass liquid weight respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding second target value ranges to construct a second target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected at the cavity volume measurement point and the second target value range; Step S4: collecting vertical load and stress value data of the vertical load measurement point at the bottom of the mold cavity, determining the third target value ranges corresponding to the vertical load and stress value respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding third target value ranges to construct a third target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the vertical load measurement point at the bottom of the mold cavity and the third target value range; Step S5: collecting heat dissipation speed and temperature uniformity data of the heat dissipation points of the mold cavity, determining fourth target value ranges corresponding to the heat dissipation speed and temperature uniformity respectively based on the storage database and design requirements, and analyzing and processing these data and the corresponding fourth target value ranges to construct a fourth target evaluation coefficient, which is used to evaluate the degree of deviation between the data collected from the heat dissipation points of the mold cavity and the fourth target value range; Step S6: respectively collecting the first acoustic wave transmission velocity parameter of the cavity wall contact point and the second acoustic wave transmission velocity parameter of the cavity heat dissipation point, and analyzing and processing the first acoustic wave transmission velocity parameter and the second acoustic wave transmission velocity parameter to generate a calibration coefficient, which is used to correct the first target evaluation coefficient and the fourth target evaluation coefficient respectively; Step S7: respectively determining the target values ​​of the third target evaluation coefficient, and the corrected first target evaluation coefficient and the fourth target evaluation coefficient, and inputting the determined target values ​​into the multi-objective optimization algorithm to dynamically adjust the contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation speed of the preforming mold; Step S8: Setting a judgment threshold of the second target evaluation coefficient, and only when the second target evaluation coefficient is greater than the set judgment threshold, fine-tuning the vertical load.

2. The high performance metallic glass mold optimization method based on a multi-objective optimization algorithm according to claim 1, characterized in that: Obtain the design requirements of the preforming mold in advance, including: According to the design requirements of mold material, mold size and temperature tolerance range, select molds that meet the specifications of target glass products from the existing mold database; Record the basic information of the target mold, including mold material, mold size, glass product specifications and molding process requirements; After obtaining the target mold, the design requirements of the preforming mold are specifically determined. The design requirements include the following aspects: 1) Contact requirements of glass bubble; 2) Volume and weight requirements of preform molds; 3) Vertical load and stress value requirements of the mold; 4) Requirements for heat dissipation speed and temperature uniformity of the mold; Classification marking is performed at key locations of the preform mold, including: According to the obtained design requirements, classification marks are made at the key positions of the preforming mold to form a classification set {a, b, c, d}, which is described as follows: a is a cavity wall contact point, and several positions in the cavity wall contact point are marked to form a first number set {a1, a2, ..., an}, where an represents the number index of the an-th contact position in the first number set, and an represents the total number of contact positions, and ai∈{a1, a2, ..., an} is set, where ai represents the number index of the ai-th contact position in the first number set; b is a cavity volume measurement point, and several positions in the cavity volume measurement point are marked to form a second numbering set {b1, b2, ..., bm}, where bm represents the numbering index of the volume measurement position at the bmth position in the second numbering set, and bm represents the total number of volume measurement positions, and bj∈{b1, b2, ..., bm} is set, where bj represents the numbering index of the volume measurement position at the bjth position in the second numbering set; c is a vertical load measurement point at the bottom of the mold cavity, and several positions in the measurement points at the bottom of the mold cavity are marked to form a third numbering set {c1, c2, ..., ck}, where ck represents the numbering index of the ckth measurement position in the third numbering set, and ck represents the total number of measurement positions, and cr∈{c1, c2, ..., ck} is set, where cr represents the numbering index of the crth measurement position in the third numbering set; d is a heat dissipation point of the mold cavity, and several positions in the heat dissipation points of the mold cavity are marked to form a fourth numbering set {d1, d2, ..., du}, where du represents the numbering index of the heat dissipation position at the duth position in the fourth numbering set, and du represents the total number of heat dissipation positions, and dh∈{d1, d2, ..., du} is set, where dh represents the numbering index of the heat dissipation position at the dhth position in the fourth numbering set; The working data of each key position in the classification set {a, b, c, d} is stored to form a storage database.

3. The high performance metallic glass mold optimization method based on a multi-objective optimization algorithm according to claim 2, characterized in that: Determining the value range of the first target and constructing the first target evaluation coefficient specifically include: In the first number set {a1, a2, ..., an}, the contact time, contact temperature and contact pressure at ai are marked as JCt ai , JCw ai , JTl ai , further determine the contact time JCt ai The first target value range is , and in Take the average of the two end points , and As the contact time target value of the ai-th contact position; Determine the contact temperature JCw ai The first target value range is , and in Take the average of the two end points , and As the contact temperature target value of the ai-th contact position; Determine the contact pressure JTl ai The first target value range is , and in Take the average of the two end points , and As the contact pressure target value at the ai-th contact position; The average deviations of the contact time, contact temperature and contact pressure at the contact position ai from the first target value range are calculated respectively. The calculation formula of the average deviation is as follows: ; in, , , denote the average deviations of contact time, contact temperature and contact pressure at the contact positions in the first numbered set {a1, a2, …, an} respectively; According to the above average deviation, the first target evaluation coefficient is comprehensively defined as , and its calculation formula is: ; in, , , are the weight coefficients of contact time, contact temperature and contact pressure respectively, and the values ​​of each weight coefficient are as follows: ; limited The value range is (0,1). The closer it is to 0, the smaller the deviation is, and the closer it is to 1, the greater the deviation is.

4. The high performance metallic glass mold optimization method based on a multi-objective optimization algorithm according to claim 3 is characterized in that: Determining the value range of the second target and constructing the second target evaluation coefficient specifically include: In the second number set {b1, b2, ..., bm}, the actual volume of the mold cavity and the weight of the glass liquid at bj are marked as , ; Determine the actual cavity volume The second target value range is , and in Take the average of the two end points , and As the target value of the actual volume of the mold cavity at the bjth measurement position; Determine the weight of the molten glass The second target value range is , and in Take the average of the two end points , and will be used as the target value of the glass liquid weight at the bjth measuring position; The average deviations of the actual volume of the mold cavity and the weight of the glass liquid at the bjth measurement position from the second target value range are calculated respectively. The calculation formula for the average deviation is as follows: ; in, , represent the average values ​​of the deviations of the actual volume of the mold cavity and the weight of the molten glass at the measurement positions in the second numbered set {b1, b2, …, bm} respectively; According to the above average deviation, the second target evaluation coefficient is comprehensively defined as , and its calculation formula is: ; limited The value range is (0,1). The closer it is to 0, the smaller the deviation is, and the closer it is to 1, the greater the deviation is. The values ​​of each weight coefficient are as follows: ; in, , are the weight coefficients of the actual volume of the mold cavity and the weight of the molten glass respectively.

5. The high performance metallic glass mold optimization method based on a multi-objective optimization algorithm according to claim 4, characterized in that: Determination of the value range of the third target and construction of the third target evaluation coefficient specifically include: In the third number set {c1, c2, …, ck}, the vertical load and stress values ​​at cr are marked as , ; Determine vertical load The third target value range is , and in Take the average of the two end points , and As the vertical load target value at the crth measuring position; Determine stress values The third target value range is , and in Take the average of the two end points , and As the target stress value at the crth measuring position; Calculate the average deviation between the vertical load and stress value at the cr measurement position and the third target value range. The calculation formula for the average deviation is as follows: ; in, , represent the average deviations of the vertical load and stress values ​​at the measurement positions in the third numbered set {c1, c2, …, ck}, respectively; According to the above average deviation, the third target evaluation coefficient is comprehensively defined as , and its calculation formula is: ; limited The value range is (0,1). The closer it is to 0, the smaller the deviation is, and the closer it is to 1, the greater the deviation is. The values ​​of each weight coefficient are as follows: ; in, , are the weight coefficients of vertical load and stress value respectively.

6. The high performance metallic glass mold optimization method based on a multi-objective optimization algorithm according to claim 5, characterized in that: Determination of the value range of the fourth objective and construction of the fourth objective evaluation coefficient specifically include: In the fourth numbered set {d1, d2, ..., du}, the heat dissipation rate and temperature uniformity at dh are marked as , ; Determine the heat dissipation rate The fourth target value range is , and in Take the average of the two end points , and As the heat dissipation speed target value at the heat dissipation position at dh; Determining Temperature Uniformity The fourth target value range is , and in Take the average of the two end points , and As the temperature uniformity target value of the heat dissipation position at dh; The average deviations of the heat dissipation speed and temperature uniformity at the heat dissipation position dh from the fourth target value range are calculated respectively. The calculation formula for the average deviation is as follows: ; in, , represent the average values ​​of the deviation of the heat dissipation speed and the temperature uniformity in the heat dissipation position in the fourth numbered set {d1, d2, …, du} respectively; According to the above average deviation, the fourth target evaluation coefficient is comprehensively defined as , and its calculation formula is: ; limited The value range is (0,1). The closer it is to 0, the smaller the deviation is, and the closer it is to 1, the greater the deviation is. The values ​​of each weight coefficient are as follows: ; in, , are the weight coefficients of heat dissipation speed and temperature uniformity respectively.

7. The high performance metallic glass mold optimization method based on a multi-objective optimization algorithm according to claim 6, characterized in that: In the first number set {a1, a2, ..., an}, the first acoustic wave transmission velocity parameter collected at the cavity wall contact point ai is recorded as SW1 ai ; In the fourth numbered set {d1, d2, ..., du}, the second acoustic wave transmission velocity parameter collected at the heat dissipation point dh of the mold cavity is recorded as SW2 dh ; According to the storage database and the standard manual referenced by the design requirements, the standard values ​​of the first sound wave conduction velocity parameter and the second sound wave conduction velocity parameter are determined as follows: and , further calculate the calibration coefficients K1 and K4: ; Use the calibration coefficients K1 and K4 to calibrate the first target evaluation coefficients respectively and the fourth objective evaluation coefficient , the correction formula is as follows: ; in, represents the corrected first objective evaluation coefficient, Represents the fourth objective evaluation coefficient after correction.

8. The high performance metallic glass mold optimization method based on a multi-objective optimization algorithm according to claim 7, characterized in that: The target values ​​are input into a multi-objective optimization algorithm to dynamically adjust the preform die contact time, contact temperature, contact pressure, vertical load, stress value and heat dissipation rate, including: 1.1) According to the process requirements and design requirements of the preforming mold, determine the following target values: Determine the third target evaluation coefficient The target value is ; Determine the corrected first target evaluation coefficient and the fourth objective evaluation coefficient The target values ​​of and ; 2.1) Contact time Adjustments: when Greater than The adjustment strategy is as follows: like Greater than 105% multiple value, you need to reduce ; like exist If the value is below 105%, it is necessary to maintain Current value; The mathematical expression of the adjustment is as follows: ; in, is the proportionality constant, , for and The difference, for Adjustment amount; 2.2) For contact temperature Adjustments: when Greater than The adjustment strategy is as follows: like Greater than 107% multiple value, you need to reduce ; like exist If the value is below 107%, it is necessary to maintain Current value; The mathematical expression of the adjustment is as follows: ; in, is the proportionality constant, , for and The difference, for Adjustment amount; 2.3) For contact pressure Adjustments: when Greater than The adjustment strategy is as follows: like Greater than 104% multiple value, you need to reduce ; like exist If the value is below 104%, it is necessary to maintain Current value; The mathematical expression of the adjustment amount is as follows: ; in, is the proportionality constant, , for and The difference, for Adjustment amount; 2.4) For vertical load Adjustments: when Greater than The adjustment strategy is as follows: like Greater than 106% multiple value, you need to reduce ; like exist If the value is below 106%, it is necessary to maintain Current value; The mathematical expression of the adjustment amount is as follows: ; in, is the proportionality constant, , for and The difference, for Adjustment amount; 2.5) For stress values Adjustments: when Greater than The adjustment strategy is as follows: like Greater than 108% multiple value, you need to reduce ; like exist If the value is below 108% of the Current value; The mathematical expression of the adjustment amount is as follows: ; in, is the proportionality constant, , for and The difference, for Adjustment amount; 2.6) Regarding heat dissipation speed Adjustments: when Greater than The adjustment strategy is as follows: like Greater than 109% multiple value, you need to reduce ; like exist If the value is below 109% of the Current value; The mathematical expression of the adjustment amount is as follows: ; in, is the proportionality constant, , for and The difference, for Adjustment amount.

9. The high performance metallic glass mold optimization method based on a multi-objective optimization algorithm according to claim 8, characterized in that: Set the second target evaluation coefficient The judgment threshold is Q1, and 0.34≤Q1≤0.67, and the reference value of Q1 is set to 0.

56. When the vertical load is adjusted, the fine-tuning formula is as follows: ; in, is the vertical load adjustment The value after fine-tuning.