A metal forging equipment intelligent control method and system

Abstract

The present invention discloses an intelligent control method and system for metal forging equipment, which relates to the field of metal forging technology. In the process of applying pressure, the flow state of the plastic blank and the ability of the internal resistance to flow are monitored in real time, so that the operator can adjust the forging parameters in time, and further avoid the phenomenon of insufficient flow or excessive flow. Based on the heat flux density and the pressure change data in the mold, the full cavity evaluation coefficient Mgz is calculated in combination with the prediction model, so that it is possible to accurately judge whether the plastic blank fills the entire mold cavity, further avoiding the empirical judgment in the traditional method and improving the scientific nature of the evaluation. By performing laser scanning and difference coefficient calculation on the surface of the formed metal forging, surface defects such as oxide scale can be effectively identified and processed, thereby improving the surface finish and mechanical properties of the forging. The process optimization is continued according to the surface difference coefficient Bcxs to form a closed-loop feedback mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of metal forging, and in particular to an intelligent control method and system for metal forging equipment. Background Art

[0002] In modern manufacturing, metal processing is an extremely important field, involving multiple links from the selection of raw materials to the manufacture of final products. Especially in the field of metal processing, metal forging, as an important manufacturing process, uses pressure to shape metal billets and is widely used in industries such as aviation, automobiles and machinery. With the advancement of manufacturing technology, the intelligent upgrade of metal forging equipment has become a trend in the development of the industry.

[0003] In the optimization of the forging process of metal billets, the existing forging processes usually face some shortcomings, such as inaccurate temperature and pressure control, insufficient real-time monitoring of flow state, etc., which may lead to unstable quality of forged parts. Traditional methods often rely on empirical judgment, but lack systematic real-time data analysis, making it difficult to effectively identify and solve potential problems that arise in the forging process. This limitation not only affects the consistency and reliability of the product, but may also increase material waste and production costs. Therefore, the forging process optimization method based on intelligent control technology came into being, aiming to improve the accuracy and efficiency of the forging process through real-time monitoring, data analysis and feedback control, thereby improving the overall quality of metal forgings. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent control method and system for metal forging equipment, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A metal forging equipment intelligent control method, comprising the following steps:

[0006] S1. Collecting property information of the metal blank to be forged in advance, obtaining relevant property characteristic data, heat treating the metal blank to be forged, setting corresponding forging pressure, generating a plastic blank, and placing it on a closed die;

[0007] S2. Apply pressure to the closed die through metal forging equipment, and after the pressure is applied, monitor the state of the plastic blank in the closed die in real time to obtain relevant flow state data, and analyze the ability of the plastic blank to resist flow based on the relevant flow state data to obtain the shear stress Jy. According to the shear stress Jy value, preliminarily judge whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank. If not, return the plastic blank to the process;

[0008] S3. Based on step S2, a metal forging device is used to apply pressure to the plastic blank. During the pressure application process, the pressure change data in the closed mold and the temperature change data at different positions are monitored in real time to calculate the heat flux density Rmd at different areas. According to the heat flux density Rmd and the pressure change data in the closed mold, combined with the trained forging prediction model, the full cavity evaluation coefficient Mgz is obtained by fitting.

[0009] S4. Pre-set the evaluation threshold Q, and compare the evaluation threshold Q with the full cavity evaluation coefficient Mgz to determine whether the plastic blank fills the entire mold cavity. If it is completely filled, the formed metal forging will enter the peeling process, and the surface of the metal forging after the peeling process will be laser scanned to obtain three-dimensional data, and the surface difference coefficient Bcxs will be calculated. According to the surface difference coefficient Bcxs, the process of the formed metal forging will continue to be optimized.

[0010] Preferably, the specific steps of S1 include:

[0011] S11, collecting attribute information of the metal blank to be forged in advance to obtain relevant attribute characteristic data, wherein the relevant attribute characteristic data include the content of various alloy elements in the metal blank to be forged, the mass-to-volume ratio of the metal blank to be forged, the melting point of the metal blank to be forged, the viscosity μ of the plastic blank during flow, and the mechanical properties of the metal blank to be forged, wherein the mechanical properties include yield strength, tensile strength, ductility and hardness;

[0012] S12. Based on the relevant property characteristic data obtained in S11, the metal blank to be forged is heat treated and a corresponding forging pressure is set to generate a plastic blank, wherein the heat treatment includes placing the metal blank to be forged into a heating furnace to plasticize the metal blank to be forged.

[0013] Preferably, the specific steps of S2 include:

[0014] S21. According to the content of S12, a metal forging device is used to apply a corresponding forging pressure to the closed die, and after the pressure is applied, the state of the plastic blank in the closed die is monitored in real time to obtain relevant flow state data, wherein the relevant flow state data includes the flow velocity jnd of the plastic blank under the corresponding forging pressure and the distance y perpendicular to the flow direction.

[0015] Preferably, S2 also includes:

[0016] S22. Analyze the ability of the plastic blank to resist flow according to the relevant flow state data, and obtain the shear stress Jy after dimensionless processing. The shear stress Jy is obtained by the following formula:

[0017]

[0018] In the formula, μ is the physical property of the plastic blank, which indicates the viscosity of the plastic blank when it flows; jnd indicates the flow velocity of the plastic blank; y indicates the distance perpendicular to the flow direction; d(jnd) indicates the change in the flow velocity of the plastic blank; d(y) indicates the change in position in the vertical direction; It indicates the rate of change of the speed of the plastic blank per unit distance;

[0019] S23. According to the shear stress Jy value, the shear stress Jy is compared and analyzed with the preset safety range to preliminarily determine whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank. The specific determination content is as follows:

[0020] S231. If the shear stress Jy falls within the preset safety range, it is preliminarily determined that the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank;

[0021] S232. If the shear stress Jy does not fall within the preset safety range, it is preliminarily determined that the forging temperature and forging pressure of the current plastic blank during heat treatment do not meet the forging requirements of the corresponding metal blank. If not, the plastic blank is returned to the process, and the forging temperature and forging pressure are adjusted until the shear stress Jy falls within the preset safety range, at which point the return process is stopped.

[0022] Preferably, the specific steps of S3 include:

[0023] S31, based on the forging temperature and forging pressure finally adjusted in step S2, applying corresponding forging pressure to the plastic blank by using metal forging equipment;

[0024] S32. Divide the inner wall area of ​​the closed mold into several groups of areas on an even basis, and monitor the pressure change data in the closed mold and the temperature change data in different areas in real time during the pressure application process, wherein the pressure change data in the closed mold includes the pressure difference Yzc at different monitoring intervals in the closed mold; the temperature change data in different areas in the closed mold includes the temperature Wd and thermal conductivity Dxs at the corresponding areas in the closed mold.

[0025] Preferably, S3 also includes:

[0026] S33, based on the temperature change data at different areas in the closed mold, the heat flux density Rmd at different areas is obtained, which is specifically obtained by the following method:

[0027]

[0028] Where Dxs is the thermal conductivity; Wd is the temperature in the corresponding area of ​​the closed mold; d(Wd) is the change in temperature in the corresponding area of ​​the closed mold. It represents the rate of change of temperature with distance.

[0029] Preferably, S3 also includes:

[0030] S34. Use convolutional neural network technology to build a forging prediction model, input the heat flux density Rmd and the pressure change data in the closed die into the forging prediction model, and after dimensionless processing, map the corresponding data values ​​to the interval [0,1] to obtain the full cavity evaluation coefficient Mgz by fitting, which is obtained in the following way:

[0031]

[0032] Where n is the monitoring period; m is the number of monitoring intervals; i = 1, 2, 3, ..., n; j = 1, 2, 3, ..., m; α and β are weight values; H is the correction constant; Rmdc i Expressed as the heat flux difference in the i-th monitoring period; Rmdc avg Expressed as the average value of heat flux difference; Yzc j Expressed as the pressure difference at the jth monitoring interval; Yzc avg Expressed as the average value of the pressure difference.

[0033] Preferably, the specific steps of S4 include:

[0034] S41, by comparing the evaluation threshold Q with the full cavity evaluation coefficient Mgz, to determine whether the plastic blank fills the entire mold cavity, the specific determination content is as follows:

[0035] S411, if the full cavity evaluation coefficient Mgz exceeds the evaluation threshold value Q, it is determined that the plastic blank does not fill the entire die cavity, and at this time, an instruction to continue to apply pressure to the plastic blank using the metal forging equipment is issued to the outside, until the full cavity evaluation coefficient Mgz does not exceed the evaluation threshold value Q, then the instruction to continue to apply pressure to the plastic blank using the metal forging equipment is stopped;

[0036] S412: If the full cavity evaluation coefficient Mgz does not exceed the evaluation threshold Q, it is determined that the plastic blank fills the entire mold cavity.

[0037] Preferably, S4 also includes:

[0038] S42, when the plastic blank fills the entire die cavity, the formed metal forging enters a peeling process, and the outer surface of the formed metal forging is divided into a plurality of groups of monitoring areas of equal area, and the surface of the metal forging after the peeling process is laser scanned to obtain three-dimensional data, wherein the three-dimensional data includes the oxide scale area PMj in each monitoring area on the outer surface of the formed metal forging;

[0039] S43, based on the three-dimensional data in S42, calculate and obtain the surface difference coefficient Bcxs, which is specifically obtained in the following way:

[0040]

[0041] Where P represents the number of monitoring areas, p = 1, 2, 3, ..., P, PMj p It is expressed as the oxide scale area in the pth monitoring area, Expressed as the average value of the oxide scale area, Pmj σ Expressed as the standard deviation of the scale area.

[0042] S44, by comparing the surface difference coefficient Bcxs with the preset threshold value, to analyze whether it is necessary to continue to perform peeling treatment on the formed metal forging, the specific content is as follows:

[0043] If the surface difference coefficient Bcxs exceeds the preset threshold, the peeling process will continue to be performed on the formed metal forging until the surface difference coefficient Bcxs does not exceed the preset threshold, and then the peeling process will be stopped;

[0044] If the surface difference coefficient Bcxs does not exceed the preset threshold value, the peeling operation of the formed metal forging will be terminated.

[0045] An intelligent control system for metal forging equipment, comprising a preparation module, a preliminary optimization analysis module, a filling control module and a forging surface optimization module;

[0046] The preparation module is used to collect property information of the metal blank to be forged in advance, obtain relevant property characteristic data, perform heat treatment on the metal blank to be forged, set corresponding forging pressure, generate plastic blank, and place it on the closed die;

[0047] The preliminary optimization analysis module is used to apply pressure to the closed die through the metal forging equipment, and after the pressure is applied, monitor the state of the plastic blank in the closed die in real time to obtain relevant flow state data, and analyze the ability of the plastic blank to resist flow inside based on the relevant flow state data to obtain the shear stress Jy, and preliminarily judge whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank according to the shear stress Jy value, and if not, perform a return operation on the plastic blank;

[0048] The filling control module applies pressure to the plastic blank using metal forging equipment, and during the pressure application process, monitors the pressure change data in the closed mold and the temperature change data at different positions in real time to calculate and obtain the heat flux density Rmd at different areas, and obtains the full cavity evaluation coefficient Mgz by fitting according to the heat flux density Rmd and the pressure change data in the closed mold, combined with the trained forging prediction model;

[0049] The forging surface optimization module is used to pre-set an evaluation threshold Q, and compare the evaluation threshold Q with the full cavity evaluation coefficient Mgz to determine whether the plastic blank fills the entire mold cavity. If it is completely filled, the formed metal forging will enter the peeling process, and the surface of the metal forging after the peeling process will be laser scanned to obtain three-dimensional data, and the surface difference coefficient Bcxs will be calculated. According to the surface difference coefficient Bcxs, the process optimization of the formed metal forging will continue.

[0050] The present invention provides a metal forging equipment intelligent control method and system, which has the following beneficial effects:

[0051] (1) During the process of applying pressure, the flow state of the plastic blank and its internal resistance to flow are monitored in real time, so that the operator can adjust the forging parameters in time to further avoid the phenomenon of insufficient flow or excessive flow. Based on the heat flux density and the pressure change data in the mold, the full cavity evaluation coefficient Mgz is calculated in combination with the prediction model, so that it is possible to accurately judge whether the plastic blank fills the entire mold cavity, further avoiding the empirical judgment in the traditional method and improving the scientific nature of the evaluation. By laser scanning and calculating the difference coefficient of the formed metal forging surface, surface defects such as oxide scale can be effectively identified and processed, thereby improving the surface finish and mechanical properties of the forging. According to the surface difference coefficient Bcxs, the process optimization is continued to form a closed-loop feedback mechanism, so that the production process can be continuously improved, adapted to different materials and production requirements, and reduce the scrap rate. By accurately controlling the forging parameters and real-time monitoring, unnecessary heat treatment and processing links are reduced, thereby effectively reducing production energy consumption and material waste, and achieving higher economic benefits. Combined with advanced sensing technology and data analysis, the intelligence level of metal forging equipment is improved, and the forging industry is promoted to transform to intelligent manufacturing, which is in line with the trend of future industrial development. In summary, this method not only improves the efficiency and product quality of metal forging, but also promotes the intelligent and refined development of forging technology, and has broad application prospects and market value.

[0052] (2) By applying forging pressure and monitoring the flow state data of the plastic blank in real time, it is ensured that potential problems can be discovered and handled in time during the forging process, thereby enhancing the safety and reliability of the production process. Obtaining the flow velocity of the plastic blank and the distance perpendicular to the flow direction can deeply understand the flow behavior of the material in the mold, provide important data support for subsequent optimization, and improve the overall grasp of the forging process. Through dimensionless processing and calculation of shear stress Jy, a quantitative analysis of the flow resistance of the plastic blank is provided, making the material performance evaluation under forging conditions more accurate, thereby providing a basis for optimizing process parameters. Comparing and analyzing the shear stress Jy with the preset safety range effectively avoids material damage caused by excessive flow resistance, ensuring the safety of the forging process and the quality of the finished product. If the shear stress Jy does not fall within the preset safety range, the system can automatically trigger the return operation, adjust the forging temperature and pressure in time, realize intelligent control of the process, and avoid errors caused by human intervention. Through real-time monitoring and feedback, the probability of rework caused by improper temperature and pressure is reduced, thereby improving overall production efficiency and reducing production costs. Continuous collection of flow state data and shear stress analysis results provides data support for further optimization of materials and processes, and promotes the innovation and progress of forging technology.

[0053] (3) Dividing the inner wall of the closed mold into multiple areas can monitor the pressure and temperature changes in each area more carefully, making the understanding of the internal environment of the mold more comprehensive and helping to find potential hot spots or uneven pressure problems. Real-time acquisition of the pressure difference Yzc in the closed mold provides important data for analyzing the flow and forming of the plastic billet in the mold. By obtaining the heat flux density Rmd in different areas, the thermal conductivity of the closed mold can be scientifically evaluated to provide data support for ensuring uniform heating and flow of the metal in the mold and reduce forging defects caused by uneven heat. By monitoring pressure and temperature changes, dynamic adjustments can be made during the production process, effectively avoiding production problems caused by insufficient or excessive material flow, and improving production flexibility and adaptability. Combined with the analysis results of heat flux density and pressure difference, it can provide data support for the optimization of the forging process, promote continuous improvement of the forging process, and improve production efficiency and product quality.

[0054] (4) By constructing a forging prediction model, the full cavity evaluation coefficient Mgz can be accurately fitted, providing a scientific basis for judging the filling condition of the plastic blank in the die cavity, and improving the controllability of the forging process. By using dimensionless processed data mapping, the model can automatically learn and adapt to different forging conditions, thereby providing more efficient support for real-time decision-making, reducing manual intervention, and timely judging whether the plastic blank fills the entire die cavity, effectively avoiding the waste of resources caused by insufficient filling, ensuring the rational use of materials in the forging process, and improving production efficiency.

[0055] (5) By introducing the surface difference coefficient Bcxs, the surface quality analysis of forgings becomes more intelligent, and the uniformity of the oxide scale can be monitored in real time, providing a scientific basis for subsequent processing. By comparing with the preset threshold, it can effectively determine whether the peeling process needs to be continued, avoiding unnecessary processing operations, saving time and resources, and improving work efficiency. Real-time monitoring and analysis of the oxide scale area can detect and deal with surface quality problems early, reduce the scrap rate caused by surface defects, and improve the production qualification rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a schematic flow chart of an intelligent control method for metal forging equipment according to the present invention;

[0057] Figure 2 This is a block diagram of an intelligent control system for metal forging equipment according to the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Example 1

[0060] See also Figure 1 The present invention provides a metal forging equipment intelligent control method, comprising the following steps:

[0061] S1. Collecting property information of the metal blank to be forged in advance, obtaining relevant property characteristic data, heat treating the metal blank to be forged, setting corresponding forging pressure, generating a plastic blank, and placing it on a closed die;

[0062] S2. Apply pressure to the closed die through metal forging equipment, and after the pressure is applied, monitor the state of the plastic blank in the closed die in real time to obtain relevant flow state data, and analyze the ability of the plastic blank to resist flow based on the relevant flow state data to obtain the shear stress Jy. According to the shear stress Jy value, preliminarily judge whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank. If not, return the plastic blank to the process;

[0063] S3. Based on step S2, a metal forging device is used to apply pressure to the plastic blank. During the pressure application process, the pressure change data in the closed mold and the temperature change data at different positions are monitored in real time to calculate the heat flux density Rmd at different areas. According to the heat flux density Rmd and the pressure change data in the closed mold, combined with the trained forging prediction model, the full cavity evaluation coefficient Mgz is obtained by fitting.

[0064] S4. Pre-set the evaluation threshold Q, and compare the evaluation threshold Q with the full cavity evaluation coefficient Mgz to determine whether the plastic blank fills the entire mold cavity. If it is completely filled, the formed metal forging will enter the peeling process, and the surface of the metal forging after the peeling process will be laser scanned to obtain three-dimensional data, and the surface difference coefficient Bcxs will be calculated. According to the surface difference coefficient Bcxs, the process of the formed metal forging will continue to be optimized.

[0065] In this embodiment, by collecting various attribute information of the metal blank, the heat treatment and forging pressure can be accurately set to ensure that the generated plastic blank meets the relatively optimal fluidity, thereby improving the forging efficiency and the quality of the finished product. In the process of applying pressure, the flow state, pressure change and temperature distribution of the plastic blank are monitored in real time, and potential problems can be identified in time to ensure that the forging conditions meet the material requirements and further reduce the rework rate. By calculating the heat flux density Rmd and the full cavity evaluation coefficient Mgz, the filling situation of the mold can be quantified, and it is effective to judge whether the plastic blank completely fills the mold, and further avoid defects caused by mold gaps. The application of laser scanning technology makes the evaluation of the oxide scale on the surface of the forging more accurate. After calculating the surface difference coefficient Bcxs, the peeling treatment can be carried out in a targeted manner to improve the quality and efficiency of subsequent processing. Combined with the trained forging prediction model, the refined process optimization of the formed metal forgings is further realized, which promotes the intelligence and automation of the production process and improves the overall production efficiency and product consistency. In summary, this method effectively improves the intelligence level of metal forging equipment, optimizes the forging process, ensures product quality, and has important industrial application value.

[0066] Example 2

[0067] Please refer to Figure 1 , specifically: S1 specific steps include:

[0068] S11, collecting attribute information of the metal blank to be forged in advance to obtain relevant attribute characteristic data, wherein the relevant attribute characteristic data include the content of various alloy elements in the metal blank to be forged (such as iron, aluminum, copper, nickel, manganese, etc.), the ratio of mass to volume of the metal blank to be forged, the melting point of the metal blank to be forged, the viscosity μ of the plastic blank during flow, and the mechanical properties of the metal blank to be forged, wherein the mechanical properties include yield strength, tensile strength, ductility and hardness;

[0069] Chemical composition analysis of the metal billet to be forged to ensure that it meets the forging requirements;

[0070] S12. Based on the relevant property characteristic data obtained in S11, the metal blank to be forged is heat treated and a corresponding forging pressure is set to generate a plastic blank, wherein the heat treatment includes placing the metal blank to be forged into a heating furnace to plasticize the metal blank to be forged.

[0071] In this embodiment, by collecting the content of alloy elements in the metal blank in detail, it is possible to ensure that the chemical composition of the forging material meets the requirements, further reduce the risk of forging failure caused by inconsistent components, and improve production stability. In the heat treatment stage, the metal blank is placed in a heating furnace for plasticization treatment, so that its fluidity and processability are significantly improved. This process ensures the uniformity and plasticity of the blank when pressure is applied, thereby improving the forming quality of the forged part. Based on the obtained mass-to-volume ratio, melting point, viscosity and other attribute data, the forging pressure can be set more scientifically, so that each forging is in relatively optimal conditions, and the uniformity and precision of the finished product are improved. By evaluating the mechanical properties, the performance of the formed metal is ensured, making it more reliable and safe in subsequent applications. By accurately controlling the alloy composition and heat treatment process, it is possible to effectively reduce material waste, improve resource utilization, and meet the needs of modern manufacturing industry for sustainable development. With the help of a comprehensive analysis of the relevant attribute characteristic data, the manufacturing system can intelligently adjust the processing parameters, form a dynamic optimization mechanism, and improve the flexibility and responsiveness of the forging process. Based on the material performance evaluation, the R&D team can develop and test new alloy materials more quickly, accelerate the pace of innovation, and lay the foundation for the market promotion of high-performance forging materials. In summary, step S1 not only improves the quality and efficiency of metal forging, but also promotes the development of the entire forging process towards intelligence and refinement, and has good application prospects and market value.

[0072] Example 3

[0073] Please refer to Figure 1 , specifically: S2 specific steps include:

[0074] S21. According to the content of S12, a metal forging device is used to apply a corresponding forging pressure to the closed die, and after the pressure is applied, the state of the plastic blank in the closed die is monitored in real time to obtain relevant flow state data, wherein the relevant flow state data includes the flow velocity jnd of the plastic blank under the corresponding forging pressure and the distance y perpendicular to the flow direction.

[0075] S2 also includes:

[0076] S22. The ability of the plastic blank to resist flow is analyzed based on the relevant flow state data, and after dimensionless processing, the shear stress Jy is obtained. The shear stress Jy is obtained by the following formula:

[0077]

[0078] In the formula, μ is the physical property of the plastic blank, which indicates the viscosity of the plastic blank when it flows. The higher the viscosity, the stronger the resistance of the plastic blank when it flows; jnd indicates the flow speed of the plastic blank; y indicates the distance perpendicular to the flow direction; d(jnd) indicates the change in the flow speed of the plastic blank; d(y) indicates the change in position in the vertical direction; It indicates the rate of change of the velocity of the plastic blank per unit distance. The greater the velocity gradient, the more violent the flow of the plastic blank and the greater the shear stress. d is usually used to describe the change of a quantity.

[0079] The viscosity μ of the plastic blank during flow mentioned above can be monitored and obtained using a viscometer;

[0080] The flow velocity of the plastic blank can be monitored in real time by a flow meter or a laser Doppler velocimeter (LDV).

[0081] The distance y perpendicular to the flow direction can be accurately measured using a displacement sensor or a laser distance sensor.

[0082] S23. According to the shear stress Jy value, the shear stress Jy is compared and analyzed with the preset safety range to preliminarily determine whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank. The specific determination content is as follows:

[0083] S231. If the shear stress Jy falls within the preset safety range, it is preliminarily determined that the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank;

[0084] S232. If the shear stress Jy does not fall within the preset safety range, it is preliminarily determined that the forging temperature and forging pressure of the current plastic blank during heat treatment do not meet the forging requirements of the corresponding metal blank. If not, the plastic blank is returned to the process, and the forging temperature and forging pressure are adjusted until the shear stress Jy falls within the preset safety range, at which point the return process is stopped.

[0085] It should be noted that the preset safety range is obtained by the following method: the shear stress Jy under different forging pressures and forging temperatures is statistically analyzed, and the average shear stress Jy is obtained by statistical algorithm. and standard deviation of shear stress Jy σ ; Based on the average shear stress and standard deviation of shear stress Jy σ , set the safety range: Among them, k is a constant, usually with a value of 1-3, corresponding to different confidence levels, and the specific value is set by the user (according to actual conditions).

[0086] In this embodiment, the flow velocity and the distance perpendicular to the flow direction of the plastic blank are monitored in real time, so that the operator can timely understand the actual state of the metal blank in the mold, ensuring the efficiency and accuracy of the forging process. By analyzing the flow state data, the shear stress Jy is obtained, which provides a quantitative basis for judging the resistance of the plastic blank during the flow process, which helps to optimize the subsequent forging parameter settings. The shear stress Jy obtained after dimensionless processing simplifies the understanding of the flow properties of the plastic blank, facilitates comparative analysis under different materials and conditions, and enhances the consistency and reliability of the evaluation. By comparing the shear stress Jy with the preset safety range, it is possible to timely judge whether the forging temperature and pressure meet the requirements, reduce the risks caused by inappropriate parameters in the production process, and ensure production safety. If the shear stress Jy does not fall into the safety range, the forging temperature and pressure can be quickly adjusted to ensure that the plastic blank can be forged in the best state, improving the flexibility and adaptability of production. Through continuous monitoring and adjustment of the plastic blank, it is ensured that the forging conditions always meet the needs of the metal blank, thereby improving the qualified rate of the final product, reducing the scrap rate, and improving the overall economic benefits. Real-time data monitoring and analysis methods are used to promote the transformation of forging processes to intelligence and automation, improve production efficiency, reduce the risk of manual intervention, and enhance the level of modernization of production. Systematic data collection and analysis provide a scientific basis for subsequent decision-making, help to continuously optimize the forging process, promote technological innovation, and promote the long-term development of the enterprise. In summary, the S2 step provides important support for the refined management of the metal forging process by real-time monitoring and analysis of the flow state of the plastic billet, enhances the safety, flexibility and efficiency of production, and effectively promotes the advancement of forging technology.

[0087] Example 4

[0088] Please refer to Figure 1 , specifically: S3 specific steps include:

[0089] S31, based on the forging temperature and forging pressure finally adjusted in step S2, applying corresponding forging pressure to the plastic blank by using metal forging equipment;

[0090] S32. Divide the inner wall area of ​​the closed mold into several groups of areas on an even basis, and monitor the pressure change data in the closed mold and the temperature change data in different areas in real time during the pressure application process, wherein the pressure change data in the closed mold includes the pressure difference Yzc at different monitoring intervals in the closed mold; the temperature change data in different areas in the closed mold includes the temperature Wd and thermal conductivity Dxs at the corresponding areas in the closed mold.

[0091] S3 also includes:

[0092] S33, based on the temperature change data at different areas in the closed mold, the heat flux density Rmd at different areas is obtained, which is specifically obtained by the following method:

[0093]

[0094] Where Dxs is the thermal conductivity, which reflects the thermal conductivity of the closed mold. The unit is watt per meter per Kelvin (W / (m·K)). The higher the thermal conductivity, the stronger the closed mold's ability to conduct heat. Wd is the temperature in the corresponding area of ​​the closed mold, and d(Wd) is the change in temperature in the corresponding area of ​​the closed mold. It indicates the rate of change of temperature with distance. The larger the temperature gradient, the more obvious the temperature change within a unit distance. The negative sign indicates the flow direction of heat from the high temperature area to the low temperature area.

[0095] The thermal conductivity coefficient Dxs mentioned above can be measured by using a heat flux sensor and a thermal conductivity meter to measure the thermal conductivity of the material.

[0096] The temperature Wd in the corresponding area of ​​the closed mold can be monitored and obtained by a temperature sensor.

[0097] In this embodiment, by applying the forging temperature and pressure based on the final adjustment, the plastic flow conditions of the plastic blank in the mold are optimized, which helps to improve the overall quality and precision of the forging. The inner wall area of ​​the closed mold is divided into several groups of areas, and the pressure change data of each area is monitored in real time, so that the stress conditions of each part of the mold can be clearly understood, and the pressure changes caused by the plastic blank on the inner wall of the mold can be discovered in time; by real-time monitoring of the temperature changes in different areas of the closed mold, the uniformity of the temperature in the mold can be confirmed, so as to promote the realization of high-quality forging. The heat flux density Rmd obtained based on the temperature change data provides a quantitative analysis of the heat conduction characteristics of the mold, which helps to evaluate the thermal efficiency of the closed mold, thereby optimizing the mold design and material selection. Monitoring the thermal conductivity coefficient can deeply understand the thermal conductivity of the closed mold, improve the scientific nature of thermal management, and then improve the distribution and flow of heat during the forging process, and promote the improvement of the overall forging efficiency. The monitoring and analysis of real-time data provides a basis for timely adjustment during the forging process, can quickly respond to temperature and pressure changes, and further reduce the uncertainty in production. By uniformly monitoring each area in the die, the consistency of forgings in each production is ensured, and the number of forgings with surface defects is reduced, thereby improving the qualification rate of the final product. This step promotes the intelligent development of the metal forging process through comprehensive data collection and analysis, provides strong support for future automation and intelligent manufacturing, and promotes the industry to develop in the direction of higher efficiency and lower energy consumption. In short, the implementation of the S3 step not only improves the accuracy and safety of the metal forging process, but also improves production efficiency through real-time monitoring and dynamic adjustment, promotes the continuous optimization and intelligence of the process, and ensures the high quality and consistency of forgings.

[0098] Example 5

[0099] Please refer to Figure 1 , specifically: S3 also includes:

[0100] S34. Use convolutional neural network technology to build a forging prediction model, input the heat flux density Rmd and the pressure change data in the closed die into the forging prediction model, and after dimensionless processing, map the corresponding data values ​​to the interval [0,1] to obtain the full cavity evaluation coefficient Mgz by fitting, which is obtained in the following way:

[0101]

[0102] Where n is the monitoring period; m is the number of monitoring intervals; i = 1, 2, 3, ..., n; j = 1, 2, 3, ..., m; α and β are weight values; H is the correction constant; Rmdc i Expressed as the heat flux difference in the i-th monitoring period; Rmdc avg Expressed as the average value of heat flux difference; Yzcj Expressed as the pressure difference at the jth monitoring interval; Yzc avg It is expressed as the average value of the pressure difference, where 0<α≤1, 0<β≤1, and α+β=1. i (n―1) and Yzc j (m-1) is a normalization process to correct the sample and is used to convert the heat flux density difference Rmdc in the current i-th monitoring period into i And the pressure difference Yzc at the jth monitoring interval j These two data points are adjusted to a standardized range for subsequent analysis. By zooming in on a single point of data, the calculation accuracy can be improved, with the goal of paying more attention to the magnitude of change in a single data point relative to the entire data set.

[0103] The initial model is constructed using convolutional neural network technology, and the initial model is trained and tested with the pressure change data in the closed mold and the temperature change data at different positions. The trained initial model is used as the state recognition model, and the feature information in the state recognition model is obtained. The state recognition model is trained and tested with the acquired feature information, and finally the trained state recognition model is used as the forging prediction model.

[0104] The heat flux difference Rmdc in the i-th monitoring period mentioned above i It refers to the difference between the maximum heat flux density and the minimum heat flux density in the closed mold during the i-th monitoring period;

[0105] The pressure difference at the jth monitoring interval Yzc j It refers to the pressure change caused by the plastic blank on the inner wall of the mold at the jth monitoring interval. The pressure change in the closed mold can be monitored by a pressure sensor (Pressure Sensor) or a pressure transmitter (PressureTransmitter).

[0106] The specific steps of S4 include:

[0107] S41, by comparing the evaluation threshold Q with the full cavity evaluation coefficient Mgz, to determine whether the plastic blank fills the entire mold cavity, the specific determination content is as follows:

[0108] S411, if the full cavity evaluation coefficient Mgz exceeds the evaluation threshold value Q, it is determined that the plastic blank does not fill the entire die cavity, and at this time, an instruction to continue to apply pressure to the plastic blank using the metal forging equipment is issued to the outside, until the full cavity evaluation coefficient Mgz does not exceed the evaluation threshold value Q, then the instruction to continue to apply pressure to the plastic blank using the metal forging equipment is stopped;

[0109] S412: If the full cavity evaluation coefficient Mgz does not exceed the evaluation threshold Q, it is determined that the plastic blank fills the entire mold cavity.

[0110] In this embodiment, a convolutional neural network is used to process the heat flux Rmd and the pressure change data in the closed die, so that the forging prediction model can efficiently extract features and improve the prediction accuracy of the forging process, which provides a more scientific basis for subsequent operations. Through dimensionless processing, the data of different monitoring cycles and intervals are standardized, so that various data can be compared within the same range, thereby improving the reliability and consistency of data analysis. By real-time monitoring and calculating the full cavity evaluation coefficient Mgz, the system can instantly feedback the filling situation of the plastic blank. This dynamic monitoring mechanism helps to quickly adjust the operation and avoid potential molding defects. When the full cavity evaluation coefficient Mgz does not exceed the evaluation threshold Q, the system can judge that the plastic blank has successfully filled the mold cavity, thereby avoiding unnecessary excessive pressure and effectively reducing the waste of materials. By issuing a real-time instruction to continue to apply pressure, the forging process can be continuously optimized, production efficiency can be improved, and the plastic blank can be fully formed in the mold. The integrated convolutional neural network and feedback mechanism realize intelligent control, so that the forging process not only depends on manual experience, but also depends on data-driven decision-making, which promotes the intelligent upgrading of forging technology. By ensuring that the plastic billet fully fills the die cavity, the probability of internal defects in the forging is reduced, the quality and consistency of the final product are improved, and the market competitiveness is enhanced. The dynamic adjustment capability of the model enables the forging system to flexibly respond to process changes based on real-time data, thereby adapting to different types of metal billets and forging requirements, and improving the versatility of the production line. The comparison of the integrated evaluation threshold and the full cavity evaluation coefficient provides a scientific basis, making operational decisions more objective and scientific, and reducing operational risks. In summary, steps S3 and S4 not only improve the intelligence and automation level of the forging process by constructing a forging prediction model and a dynamic monitoring system, but also significantly improve production efficiency, material utilization and product quality, laying a solid foundation for the modernization of the metal forging industry.

[0111] Example 6

[0112] Please refer to Figure 1 Specifically, S4 also includes:

[0113] S42, when the plastic blank fills the entire die cavity, the formed metal forging enters a peeling process, and the outer surface of the formed metal forging is divided into a plurality of groups of monitoring areas of equal area, and the surface of the metal forging after the peeling process is laser scanned to obtain three-dimensional data, wherein the three-dimensional data includes the oxide scale area PMj in each monitoring area on the outer surface of the formed metal forging;

[0114] S43, based on the three-dimensional data in S42, calculate and obtain the surface difference coefficient Bcxs, which is specifically obtained in the following way:

[0115]

[0116] Where P represents the number of monitoring areas, p = 1, 2, 3, ..., P, PMj p It is expressed as the oxide scale area in the pth monitoring area, Pmj is expressed as the average value of the oxide scale area, Pmj σ It is expressed as the standard deviation of the oxide scale area. The purpose of adding one is to avoid the denominator being zero.

[0117] The oxide scale area PMj in each monitoring area on the outer surface of the formed metal forging is scanned and analyzed by a laser scanner or a 3D imaging system to obtain the oxide scale area.

[0118] S44, by comparing the surface difference coefficient Bcxs with the preset threshold value, to analyze whether it is necessary to continue to perform peeling treatment on the formed metal forging, the specific content is as follows:

[0119] If the surface difference coefficient Bcxs exceeds the preset threshold, the peeling process will continue to be performed on the formed metal forging until the surface difference coefficient Bcxs does not exceed the preset threshold, and then the peeling process will be stopped;

[0120] If the surface difference coefficient Bcxs does not exceed the preset threshold value, the peeling operation of the formed metal forging will be terminated.

[0121] The above-mentioned preset threshold value and evaluation threshold value Q can be obtained according to the threshold value method set in S2.

[0122] In this embodiment, through laser scanning and three-dimensional data analysis, the distribution and area of ​​oxide scale can be accurately identified, ensuring that the surface quality of forgings meets the specifications and improving the overall appearance of the product. The surface of the forging is divided into multiple monitoring areas, and high-precision laser scanning technology is used to ensure the comprehensiveness and accuracy of data collection, providing a reliable basis for subsequent processing. The peeling treatment is evaluated using the surface difference coefficient Bcxs to achieve data-driven decision-making and improve the scientific nature of the treatment. According to the comparison between the surface difference coefficient Bcxs and the preset threshold, the intensity and time of the peeling treatment are dynamically adjusted, further avoiding excessive treatment and unnecessary waste of resources, and improving the processing efficiency. By effectively controlling the peeling treatment, unnecessary processing steps are reduced, thereby reducing production costs and enhancing product competitiveness. Standardized monitoring and processing procedures ensure the consistency of the surface quality of forgings and improve the reliability of mass production. The real-time monitoring and feedback mechanism enables abnormal situations in the production process to be identified and handled in a timely manner, reducing the risk of potential defects. The surface quality of the final product is guaranteed, which improves customer satisfaction and trust and helps to establish a good market reputation.

[0123] Example 7

[0124] Please refer to Figure 2 ,Specifically: An intelligent control system for metal forging equipment, including a preparation module, a preliminary optimization analysis module, a filling control module and a forging surface optimization module;

[0125] The preparation module is used to collect the property information of the metal blank to be forged in advance, obtain the relevant property characteristic data, perform heat treatment on the metal blank to be forged, set the corresponding forging pressure, generate the plastic blank, and place it on the closed die;

[0126] The preliminary optimization analysis module is used to apply pressure to the closed die through the metal forging equipment, and after the pressure is applied, monitor the state of the plastic blank in the closed die in real time to obtain relevant flow state data, and analyze the ability of the plastic blank to resist flow based on the relevant flow state data to obtain the shear stress Jy. According to the shear stress Jy value, it is preliminarily judged whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank. If not, the plastic blank is returned to the operation;

[0127] The filling control module uses metal forging equipment to apply pressure to the plastic blank, and during the pressure application process, monitors the pressure change data in the closed mold and the temperature change data at different positions in real time to calculate the heat flux density Rmd in different areas. According to the heat flux density Rmd and the pressure change data in the closed mold, combined with the trained forging prediction model, the full cavity evaluation coefficient Mgz is obtained by fitting;

[0128] The forging surface optimization module is used to pre-set the evaluation threshold Q. By comparing the evaluation threshold Q with the full cavity evaluation coefficient Mgz, it is determined whether the plastic blank fills the entire die cavity. If it is completely filled, the formed metal forging will enter the peeling process, and the surface of the metal forging after the peeling process will be laser scanned to obtain three-dimensional data, and the surface difference coefficient Bcxs will be calculated. According to the surface difference coefficient Bcxs, the process optimization of the formed metal forging will continue.

[0129] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A metal forging equipment intelligent control method, characterized in that: The following steps are included: S1. Collecting property information of the metal blank to be forged in advance, obtaining relevant property characteristic data, heat treating the metal blank to be forged, setting corresponding forging pressure, generating a plastic blank, and placing it on a closed die; S2. Apply pressure to the closed die through metal forging equipment, and after the pressure is applied, monitor the state of the plastic blank in the closed die in real time to obtain relevant flow state data, and analyze the ability of the plastic blank to resist flow based on the relevant flow state data to obtain the shear stress Jy. According to the shear stress Jy value, preliminarily judge whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank. If not, return the plastic blank to the process; S3. Based on step S2, a metal forging device is used to apply pressure to the plastic blank. During the pressure application process, the pressure change data in the closed mold and the temperature change data at different positions are monitored in real time to calculate the heat flux density Rmd at different areas. According to the heat flux density Rmd and the pressure change data in the closed mold, combined with the trained forging prediction model, the full cavity evaluation coefficient Mgz is obtained by fitting. S4. Pre-set the evaluation threshold Q, and compare the evaluation threshold Q with the full cavity evaluation coefficient Mgz to determine whether the plastic blank fills the entire mold cavity. If it is completely filled, the formed metal forging will enter the peeling process, and the surface of the metal forging after the peeling process will be laser scanned to obtain three-dimensional data, and the surface difference coefficient Bcxs will be calculated. According to the surface difference coefficient Bcxs, the process of the formed metal forging will continue to be optimized.

2. The intelligent control method for metal forging equipment according to claim 1, characterized in that: The specific steps of S1 include: S11, collecting attribute information of the metal blank to be forged in advance to obtain relevant attribute characteristic data, wherein the relevant attribute characteristic data include the content of various alloy elements in the metal blank to be forged, the mass-to-volume ratio of the metal blank to be forged, the melting point of the metal blank to be forged, the viscosity μ of the plastic blank during flow, and the mechanical properties of the metal blank to be forged, wherein the mechanical properties include yield strength, tensile strength, ductility and hardness; S12. Based on the relevant property characteristic data obtained in S11, the metal blank to be forged is heat treated and a corresponding forging pressure is set to generate a plastic blank, wherein the heat treatment includes placing the metal blank to be forged into a heating furnace to plasticize the metal blank to be forged.

3. The intelligent control method for metal forging equipment according to claim 2 is characterized in that: The specific steps of S2 include: S21. According to the content of S12, a metal forging device is used to apply a corresponding forging pressure to the closed die, and after the pressure is applied, the state of the plastic blank in the closed die is monitored in real time to obtain relevant flow state data, wherein the relevant flow state data includes the flow velocity jnd of the plastic blank under the corresponding forging pressure and the distance y perpendicular to the flow direction.

4. The intelligent control method for metal forging equipment according to claim 3 is characterized in that: S2 also includes: S22. Analyze the ability of the plastic blank to resist flow according to the relevant flow state data, and obtain the shear stress Jy after dimensionless processing. The shear stress Jy is obtained by the following formula: In the formula, μ is the physical property of the plastic blank, which indicates the viscosity of the plastic blank when it flows; jnd indicates the flow velocity of the plastic blank; y indicates the distance perpendicular to the flow direction; d(jnd) indicates the change in the flow velocity of the plastic blank; d(y) indicates the change in position in the vertical direction; It indicates the rate of change of the speed of the plastic blank per unit distance; S23. According to the shear stress Jy value, the shear stress Jy is compared and analyzed with the preset safety range to preliminarily determine whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank. The specific determination content is as follows: S231. If the shear stress Jy falls within the preset safety range, it is preliminarily determined that the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank; S232. If the shear stress Jy does not fall within the preset safety range, it is preliminarily determined that the forging temperature and forging pressure of the current plastic blank during heat treatment do not meet the forging requirements of the corresponding metal blank. If not, the plastic blank is returned to the process, and the forging temperature and forging pressure are adjusted until the shear stress Jy falls within the preset safety range, at which point the return process is stopped.

5. The intelligent control method for metal forging equipment according to claim 4 is characterized in that: The specific steps of S3 include: S31, based on the forging temperature and forging pressure finally adjusted in step S2, applying corresponding forging pressure to the plastic blank by using metal forging equipment; S32. Divide the inner wall area of ​​the closed mold into several groups of areas on an even basis, and monitor the pressure change data in the closed mold and the temperature change data in different areas in real time during the pressure application process, wherein the pressure change data in the closed mold includes the pressure difference Yzc at different monitoring intervals in the closed mold; the temperature change data in different areas in the closed mold includes the temperature Wd and thermal conductivity Dxs at the corresponding areas in the closed mold.

6. The intelligent control method for metal forging equipment according to claim 5, characterized in that: S3 also includes: S33, based on the temperature change data at different areas in the closed mold, the heat flux density Rmd at different areas is obtained, which is specifically obtained by the following method: Where Dxs is the thermal conductivity; Wd is the temperature in the corresponding area of ​​the closed mold; d(Wd) is the change in temperature in the corresponding area of ​​the closed mold. It represents the rate of change of temperature with distance.

7. The intelligent control method for metal forging equipment according to claim 6, characterized in that: S3 also includes: S34. Use convolutional neural network technology to build a forging prediction model, input the heat flux density Rmd and the pressure change data in the closed die into the forging prediction model, and after dimensionless processing, map the corresponding data values ​​to the interval [0,1] to obtain the full cavity evaluation coefficient Mgz by fitting, which is obtained in the following way: Where n is the monitoring period; m is the number of monitoring intervals; i = 1, 2, 3, ..., n; j = 1, 2, 3, ..., m; α and β are weight values; H is the correction constant; Rmdc i Expressed as the heat flux difference in the i-th monitoring period; Rmdc avg Expressed as the average value of heat flux difference; Yzc j Expressed as the pressure difference at the jth monitoring interval; Yzc avg Expressed as the average value of the pressure difference.

8. The intelligent control method for metal forging equipment according to claim 1, characterized in that: The specific steps of S4 include: S41, by comparing the evaluation threshold Q with the full cavity evaluation coefficient Mgz, to determine whether the plastic blank fills the entire mold cavity, the specific determination content is as follows: S411, if the full cavity evaluation coefficient Mgz exceeds the evaluation threshold value Q, it is determined that the plastic blank does not fill the entire die cavity, and at this time, an instruction to continue to apply pressure to the plastic blank using the metal forging equipment is issued to the outside, until the full cavity evaluation coefficient Mgz does not exceed the evaluation threshold value Q, then the instruction to continue to apply pressure to the plastic blank using the metal forging equipment is stopped; S412: If the full cavity evaluation coefficient Mgz does not exceed the evaluation threshold Q, it is determined that the plastic blank fills the entire mold cavity.

9. The intelligent control method for metal forging equipment according to claim 8, characterized in that: S4 also includes: S42, when the plastic blank fills the entire die cavity, the formed metal forging enters a peeling process, and the outer surface of the formed metal forging is divided into a plurality of groups of monitoring areas of equal area, and the surface of the metal forging after the peeling process is laser scanned to obtain three-dimensional data, wherein the three-dimensional data includes the oxide scale area PMj in each monitoring area on the outer surface of the formed metal forging; S43, based on the three-dimensional data in S42, calculate and obtain the surface difference coefficient Bcxs, which is specifically obtained in the following way: Where P represents the number of monitoring areas, p = 1, 2, 3, ..., P, PMj p It is expressed as the oxide scale area in the pth monitoring area, Expressed as the average value of the oxide scale area, Pmj σ Expressed as the standard deviation of the scale area; S44, by comparing the surface difference coefficient Bcxs with the preset threshold value, to analyze whether it is necessary to continue to perform peeling treatment on the formed metal forging, the specific content is as follows: If the surface difference coefficient Bcxs exceeds the preset threshold, the peeling process will continue to be performed on the formed metal forging until the surface difference coefficient Bcxs does not exceed the preset threshold, and then the peeling process will be stopped; If the surface difference coefficient Bcxs does not exceed the preset threshold value, the peeling operation of the formed metal forging will be terminated.

10. An intelligent control system for metal forging equipment, used to implement the intelligent control method for metal forging equipment according to any one of claims 1 to 9, characterized in that: It includes preparation module, preliminary optimization analysis module, filling control module and forging surface optimization module; The preparation module is used to collect property information of the metal blank to be forged in advance, obtain relevant property characteristic data, perform heat treatment on the metal blank to be forged, set corresponding forging pressure, generate plastic blank, and place it on the closed die; The preliminary optimization analysis module is used to apply pressure to the closed die through the metal forging equipment, and after the pressure is applied, monitor the state of the plastic blank in the closed die in real time to obtain relevant flow state data, and analyze the ability of the plastic blank to resist flow inside based on the relevant flow state data to obtain the shear stress Jy, and preliminarily judge whether the forging temperature and forging pressure of the current plastic blank during heat treatment meet the forging requirements of the corresponding metal blank according to the shear stress Jy value, and if not, perform a return operation on the plastic blank; The filling control module applies pressure to the plastic blank using metal forging equipment, and during the pressure application process, monitors the pressure change data in the closed mold and the temperature change data at different positions in real time to calculate and obtain the heat flux density Rmd at different areas, and obtains the full cavity evaluation coefficient Mgz by fitting according to the heat flux density Rmd and the pressure change data in the closed mold, combined with the trained forging prediction model; The forging surface optimization module is used to pre-set an evaluation threshold Q, and compare the evaluation threshold Q with the full cavity evaluation coefficient Mgz to determine whether the plastic blank fills the entire mold cavity. If it is completely filled, the formed metal forging will enter the peeling process, and the surface of the metal forging after the peeling process will be laser scanned to obtain three-dimensional data, and the surface difference coefficient Bcxs will be calculated. According to the surface difference coefficient Bcxs, the process optimization of the formed metal forging will continue.

Images