A method for producing and checking a cold extrusion die for metal pipe joints

Abstract

The application provides a production verification method of a metal pipe joint cold extrusion die, and relates to the technical field of metal processing. The method comprises the following steps: obtaining a pipe joint extrusion feature group of a first extrusion die; generating a target three-way compressive stress distribution feature and a target blank flow feature; performing initial performance detection on the first extrusion die to generate a first die performance index set; generating a first predicted service life; and performing quality monitoring verification on the first extrusion die based on the first predicted service life. The application can solve the technical problem that the accuracy of die quality monitoring is poor due to the lack of die wear analysis under actual operation in the prior art. By analyzing the three-way compressive stress distribution and the blank flow feature of the first extrusion die during actual extrusion operation, and combining die performance to predict the service life, the quality monitoring is performed, so that the technical effect of improving the efficiency and accuracy of die quality monitoring is achieved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of metal processing, in particular to a production and verification method of a metal pipe joint cold extrusion die. BACKGROUND

[0002] In the manufacturing process of metal pipe joints, cold extrusion technology is a commonly used processing method. It makes the metal material produce plastic deformation in the die by applying high pressure, so as to obtain the required shape and size. The quality of the cold extrusion die directly affects the quality, production efficiency and cost of the pipe joint. However, in the long-term extrusion process, the die will be degraded due to wear, fatigue and other reasons, thereby affecting the product quality. Therefore, monitoring the quality of the cold extrusion die and predicting the service life of the die in advance are of great significance to ensure product quality and improve production efficiency.

[0003] At present, the existing die quality monitoring technology often detects the size, performance and the like of the dies produced on the production line, but the dies will be worn after actual operation. Even if the quality meets the requirements, the subsequent service life may not be qualified, resulting in poor die quality monitoring effect.

[0004] In summary, the prior art has the technical problem of poor die quality monitoring accuracy due to the lack of analysis of die wear under actual operation. SUMMARY

[0005] The purpose of the present application is to provide a production and verification method of a metal pipe joint cold extrusion die, which solves the technical problem in the prior art that the die quality monitoring accuracy is poor due to the lack of analysis of die wear under actual operation.

[0006] In view of the above problems, the present application provides a production and verification method of a metal pipe joint cold extrusion die, which comprises: obtaining a pipe joint extrusion feature group of a first extrusion die, wherein the pipe joint extrusion feature group comprises die basic information, target pipe joint geometric structure information, pipe joint material information and basic information of a to-be-processed blank; performing finished product quality feature distribution simulation based on the pipe joint extrusion feature group to generate target three-way pressure stress distribution features and target blank flow features; performing initial performance detection on the first extrusion die to generate a first die performance index set; performing die stress resistance analysis by combining the target three-way pressure stress distribution features, the target blank flow features and the first die performance index set to generate a first predicted service life; and performing quality monitoring verification on the first extrusion die based on the first predicted service life.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] Acquire a pipe joint extrusion feature group of the first extrusion die, wherein the pipe joint extrusion feature group comprises die basic information, target pipe joint geometric structure information, pipe joint material information and to-be-processed blank basic information; perform finished product quality feature distribution simulation based on the pipe joint extrusion feature group, generate target three-way compressive stress distribution features and target blank flow features; perform initial performance detection on the first extrusion die, generate a first die performance index set; perform die stress resistance analysis on the target three-way compressive stress distribution features, the target blank flow features and the first die performance index set, generate a first predicted service life; perform quality monitoring verification on the first extrusion die based on the first predicted service life. By analyzing the three-way compressive stress distribution and blank flow features of the first extrusion die during actual extrusion operation, and combining with the die performance to predict the service life, quality monitoring is performed, thereby achieving the technical effects of improving the efficiency and accuracy of die quality monitoring.

[0009] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the specific embodiments of the present application can be implemented according to the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only exemplary, and other drawings can be obtained by the provided drawings without creative labor for those skilled in the art.

[0011] Figure 1 A flowchart of a production verification method of a metal pipe joint cold extrusion die of the present application;

[0012] Figure 2 A flowchart of generating target three-way compressive stress distribution features and target blank flow features in the production verification method of a metal pipe joint cold extrusion die of the present application. DETAILED DESCRIPTION

[0013] The application provides a production verification method of a metal pipe joint cold extrusion die, and solves the technical problem of poor accuracy of die quality monitoring in the prior art due to lack of analysis of die wear under actual operation. By analyzing the three-way compression stress distribution and the blank flow characteristics of the first extrusion die during actual extrusion operation, and predicting the service life of the die performance, quality monitoring is performed, thereby improving the efficiency and accuracy of die quality monitoring.

[0014] The technical solutions in the application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the application, rather than all the embodiments of the application. It should be understood that the application is not limited to the example embodiments described herein. Based on the embodiments of the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the application. In addition, it should be noted that, for the convenience of description, only parts related to the application are shown in the drawings, rather than all parts.

[0015] Please refer to the drawings Figure 1 The application provides a production verification method of a metal pipe joint cold extrusion die, and solves the technical problem of poor accuracy of die quality monitoring in the prior art due to lack of analysis of die wear under actual operation. By analyzing the three-way compression stress distribution and the blank flow characteristics of the first extrusion die during actual extrusion operation, and predicting the service life of the die performance, quality monitoring is performed, thereby improving the efficiency and accuracy of die quality monitoring.

[0016] Step one: obtaining a pipe joint extrusion feature group of the first extrusion die, wherein the pipe joint extrusion feature group includes die basic information, target pipe joint geometric structure information, pipe joint material information, and basic information of a blank to be processed.

[0017] Specifically, the first extrusion die refers to a die used for extrusion processing of a pipe joint. Extrusion processing is a metal processing method in which metal materials are deformed by flowing in the cavity of the die, so as to obtain a workpiece with a required shape and size. The pipe joint extrusion feature group refers to a group of various information parameters required for the extrusion die during extrusion of the pipe joint, including die basic information, target pipe joint geometric structure information, pipe joint material information, and basic information of a blank to be processed.

[0018] The die basic information includes the size, structure, and manufacturing material of the die. The target pipe joint geometric structure information includes the shape, size, and wall thickness of the pipe joint. The pipe joint material information includes the type, hardness, and elongation of the material. The basic information of the blank to be processed includes the shape, size, and material of the blank. By obtaining the pipe joint extrusion feature group of the first extrusion die, a basis is provided for subsequent die quality monitoring, which facilitates quality monitoring in combination with the extrusion scene and improves the accuracy of quality monitoring.

[0019] Step two: simulating the quality feature distribution of the finished product based on the pipe joint extrusion feature group, to generate target three-way compression stress distribution features and target blank flow characteristics.

[0020] Specifically, the information in the pipe joint extrusion feature set is used to construct a mathematical model that can simulate the behavior of the pipe joint during extrusion. This model is usually a finite element model that takes into account factors such as the geometry of the mold, the properties of the material, and the parameters of the extrusion process. After the model is constructed, simulation analysis can be performed to obtain the stress, strain, temperature, and other distribution of the pipe joint during extrusion. The target three-directional compressive stress distribution feature refers to the distribution of compressive stress in three directions of the pipe joint during extrusion. In cold extrusion, the material is placed in the first extrusion die, and then the material flows and forms in the cavity of the first extrusion die through the force of the extruder. Due to the closed nature of the mold, the material will be subjected to pressure from three directions during flow, which helps the material flow uniformly in the mold, reduces defects, and improves the density and mechanical properties of the finished product. Three-directional compressive stress usually refers to the three main stresses that the material is subjected to during extrusion, namely the principal stress (axial stress), transverse stress (radial stress), and shear stress.

[0021] At the same time, the target blank flow feature refers to the flow behavior of the blank in the mold cavity during extrusion, including the flow rate, flow line, filling condition, etc. These flow characteristics are very important to ensure the dimensional accuracy and internal quality of the pipe joint. The target three-directional compressive stress distribution feature and the target blank flow feature obtained by simulation can monitor the quality of the mold.

[0022] Step three: Perform initial performance detection on the first extrusion die to generate a first die performance index set.

[0023] Specifically, initial performance detection refers to detecting the material properties of the first extrusion die such as hardness, toughness, etc. For example, the hardness, toughness, tensile strength, yield strength, fatigue strength, etc. of the first extrusion die can be detected to generate a first die performance index set, reflecting the performance and expected service life of the die during extrusion, and assisting in mold quality monitoring.

[0024] Step four: Perform mold stress resistance analysis combining the target three-directional compressive stress distribution feature, the target blank flow feature, and the first die performance index set to generate a first predicted service life.

[0025] Specifically, by combining the first die performance index set, the hardness, toughness, and other performance indicators of the die are combined with the target three-directional compressive stress distribution feature and the target blank flow feature to evaluate the die's resistance to various stresses under actual working conditions and predict the service life of the die under specific working conditions. The first predicted service life, i.e. the expected service life of the die under specific working conditions, can reflect the quality of the die and ensure the accuracy of the mold quality monitoring.

[0026] Step five: quality monitoring verification of the first extrusion die based on the first predicted service life.

[0027] Specifically, the manufacturer will calibrate a standard service life when the die is shipped, thereby determining whether the first predicted service life meets the standard service life. If so, it means that the quality monitoring verification is passed, otherwise, it is not passed. Thus, by analyzing the three-directional compressive stress distribution and the blank flow characteristics of the first extrusion die during actual extrusion operation, and combining the die performance to predict the service life, the quality monitoring is carried out, thereby improving the efficiency and accuracy of die quality monitoring.

[0028] Further, as shown in the accompanying drawings, Figure 2 Step two of the present application includes:

[0029] Based on the pipe joint material information, material parameter conversion is performed to generate a material parameter set; finite element modeling is performed based on the die basic information, the target pipe joint geometric structure information, the to-be-processed blank basic information, and the material parameter set to generate a first cold extrusion finite element model; a finite boundary condition is constructed; the first cold extrusion finite element model is driven and simulated based on the finite boundary condition, and a three-directional compressive stress distribution data set and a blank flow characteristic data set are recorded; die stress against boundary analysis is performed on the three-directional compressive stress distribution data set and the blank flow characteristic data set to generate the target three-directional compressive stress distribution characteristics and the target blank flow characteristics.

[0030] Specifically, based on the pipe joint material information, material parameter conversion is performed to generate a material parameter set, which is to convert the actual properties of the material into parameters that can be used for finite element analysis. Material parameters include the elastic modulus, yield strength, Poisson's ratio, and thermal expansion coefficient of the material. These parameters can be obtained based on the material information using existing technology, and will not be described here. Next, finite element modeling is performed based on the die basic information, the target pipe joint geometric structure information, the to-be-processed blank basic information, and the material parameter set to generate a first cold extrusion finite element model. Finite element modeling is a numerical analysis method that divides complex geometric structures into small elements and applies physical laws to these elements to simulate the overall behavior of the structure. In this process, the geometry of the die and the blank is accurately modeled, and material parameters are assigned to these elements to simulate the actual extrusion process.

[0031] The limited boundary condition is constructed to simulate the influence of extrusion parameters such as extrusion speed, extrusion ratio, etc. on the interaction between the die and the blank. The limited boundary condition includes extrusion speed, extrusion ratio, etc. to ensure the accuracy of the simulation. The first cold extrusion finite element model is driven and simulated multiple times with the limited boundary condition. During the simulation, the flow and deformation of the blank in the die cavity, as well as the stress distribution generated thereby, are calculated. The three-directional compressive stress distribution data obtained from each simulation form a three-directional compressive stress distribution dataset, and the blank flow characteristic data obtained from each simulation form a blank flow characteristic dataset.

[0032] Finally, the three-directional compressive stress distribution dataset and the blank flow characteristic dataset are subjected to die stress counter boundary analysis, aiming to evaluate the stress level of the die and the flow behavior of the blank during the extrusion process, thereby generating target three-directional compressive stress distribution characteristics and target blank flow characteristics, to ensure the accuracy of the die quality monitoring.

[0033] Further, the present application also includes the following steps:

[0034] The limited boundary condition includes die extrusion parameters and extrusion environment. The preset application scenario of the first extrusion die is obtained, the historical extrusion parameters and historical extrusion environment in the preset application scenario are retrieved, and the extrusion parameter record dataset and the extrusion environment record dataset are generated. The extrusion parameter record dataset and the extrusion environment record dataset are subjected to stepwise merging to generate multiple stepwise extrusion parameters and multiple stepwise extrusion environments. The limited boundary condition is generated based on the multiple stepwise extrusion parameters and the multiple stepwise extrusion environments.

[0035] Specifically, the steps of constructing the limited boundary condition are as follows:

[0036] Firstly, the limited boundary condition includes die extrusion parameters and extrusion environment. The extrusion parameters involve the force and displacement applied to the die during the extrusion process, such as extrusion speed, extrusion ratio, friction coefficient, etc. The extrusion environment includes temperature, lubrication conditions, etc. during the extrusion process. In order to generate the limited boundary condition, first of all, the preset application scenario of the first extrusion die needs to be obtained, that is, the scenario in which the first extrusion die is used for cold extrusion work after passing the quality inspection. The specific application scenario needs to be determined in combination with the actual situation, such as the extrusion of pipe joints with specific shapes and specific materials. From this, the historical extrusion parameters and historical extrusion environment in the preset application scenario are obtained, and the extrusion parameter record dataset and the extrusion environment record dataset are generated. It should be noted that the extrusion parameter record dataset and the extrusion environment record dataset respectively contain multiple sets of different extrusion parameters and extrusion environments.

[0037] Next, the extrusion parameter record data set and the extrusion environment record data set are stepwise combined, which means that different extrusion parameters or extrusion environments are organized according to certain logical relationships to form a series of stepwise data sets. For example, the extrusion parameter record data set and the extrusion environment record data set can be divided into steps according to a preset step division threshold. The mean value of the data in each step is calculated, and thus an extrusion parameter or an extrusion environment of each step is obtained, thereby generating multiple stepwise extrusion parameters and multiple stepwise extrusion environments.

[0038] Then, the multiple stepwise extrusion parameters and the multiple stepwise extrusion environments are used to generate a limited boundary condition. That is, in the process of finite element simulation by the first cold extrusion finite element model, the limited boundary condition will change according to different extrusion parameters and extrusion environments of the extrusion process to more truly reflect the dynamic changes in the actual extrusion process, thereby driving the first cold extrusion finite element model to simulate and predict the mold performance and the behavior of the blank under different extrusion parameters and environments, so as to predict the service life of the mold, ensure the adaptability of mold quality analysis to actual operation scenarios, and thus improve the mold quality monitoring precision.

[0039] Further, the present application further includes the following steps:

[0040] Based on the three-way compressive stress distribution data set, mold adversarial loss maximization analysis is performed to generate the target three-way compressive stress distribution feature; based on the blank flow feature data set, mold adversarial loss maximization analysis is performed to generate the target blank flow feature.

[0041] Further, the present application further includes the following steps:

[0042] The three-way compressive stress distribution data set is subjected to distributed mold stress adversarial index identification to generate a mold distributed adversarial index set; and based on the mold distributed adversarial index set, the three-way compressive stress distribution data set is subjected to index maximization mapping to generate the target three-way compressive stress distribution feature.

[0043] Specifically, the steps of mold stress adversarial boundary analysis on the three-way compressive stress distribution data set and the blank flow feature data set are as follows:

[0044] The mold counter-attack loss maximization analysis based on the three-way compressive stress distribution dataset is to determine the maximum stress that the mold can withstand during the extrusion process, so as to generate the target three-way compressive stress distribution characteristics. Specifically, first, the three-way compressive stress distribution dataset is analyzed to identify the maximum stress point that the mold can withstand during the extrusion process. Then, the mold counter-attack loss maximization analysis is performed, that is, the loss of the mold when it withstands the maximum stress is evaluated, including the evaluation of the wear, fatigue life and potential structural damage of the mold, to determine whether the design of the mold is strong enough to withstand the stress in the actual extrusion process. Next, based on the analysis results, the target three-way compressive stress distribution characteristics are generated. The target three-way compressive stress distribution characteristics include the maximum stress value that the mold can withstand during the extrusion process and the distribution characteristics of the stress.

[0045] Similarly, the mold counter-attack loss maximization analysis based on the billet flow characteristics dataset is to determine the influence of the billet flow behavior on the mold during the extrusion process, so as to generate the target billet flow characteristics. First, the billet flow characteristics dataset is analyzed to evaluate the influence of the billet flow behavior on the wear and fatigue life of the mold, including the evaluation of the shear stress, friction and temperature change caused by the billet flow. Next, based on the analysis results, the target billet flow characteristics are generated. The target billet flow characteristics include the velocity distribution of the billet in the mold cavity. Through these analyses, the performance and potential problems of the mold during the extrusion process can be better understood, thereby providing strong support for mold quality monitoring to improve the accuracy of quality monitoring.

[0046] The specific steps of generating the target three-way compressive stress distribution characteristics based on the three-way compressive stress distribution dataset are as follows:

[0047] First, the distributed mold stress counter-attack index identification is performed on the three-way compressive stress distribution dataset, which is to extract the indexes that can reflect the stress resistance of the mold from the three-way compressive stress distribution dataset. These indexes will constitute the mold distributed counter-attack index set. Specifically, the stress peaks at different positions are identified as the distributed mold stress counter-attack indexes. Next, based on the mold distributed counter-attack index set, the index maximization mapping is performed on the three-way compressive stress distribution dataset, that is, the stress distribution in the three-way compressive stress distribution dataset is compared with the mold distributed counter-attack index set to find the stress distribution characteristics corresponding to the maximum counter-attack index in the three-way compressive stress distribution dataset, that is, to determine the maximum stress that the different regions of the mold can withstand, to form the target three-way compressive stress distribution characteristics, so as to realize the service life prediction under specific working conditions and improve the accuracy of mold quality monitoring.

[0048] Similarly, the steps of obtaining the target billet flow characteristics are the same as those of obtaining the target three-way compressive stress distribution characteristics, which will not be described here.

[0049] Further, step four of the present application comprises:

[0050] Based on the target three-way compressive stress distribution characteristics, the target blank flow characteristics, and the first set of die performance indicators, a continuous die wear analysis is performed to generate a wear indicator time sequence. A preset wear indicator threshold is constructed, wherein the preset wear indicator threshold is the wear indicator when the die quality is unqualified. In combination with the preset wear indicator threshold and the wear indicator time sequence, a service life that meets the preset wear indicator threshold is generated as the first predicted service life.

[0051] Further, the present application further comprises the following steps:

[0052] A die wear indicator is defined, and a die wear continuous identification module is constructed based on the die wear indicator. The target three-way compressive stress distribution characteristics, the target blank flow characteristics, and the first set of die performance indicators are analyzed by the die wear continuous identification module to output the wear indicator time sequence.

[0053] Specifically, based on the target three-way compressive stress distribution characteristics, the target blank flow characteristics, and the first set of die performance indicators, a continuous die wear analysis is performed to evaluate the wear of the first extrusion die during long-term use and predict its service life. First, the target three-way compressive stress distribution characteristics and the target blank flow characteristics are used in combination with the first set of die performance indicators to perform a continuous die wear analysis. Specifically, the wear rate and degree of the first extrusion die during the extrusion process are identified to generate a wear indicator time sequence, i.e., the change of die wear over time. Then, a preset wear indicator threshold is constructed, which is the wear indicator when the die quality is unqualified. That is, when the wear of the die reaches or exceeds the preset wear indicator threshold, the performance of the die will no longer meet the production requirements. Next, in combination with the preset wear indicator threshold and the wear indicator time sequence, a service life that meets the preset wear indicator threshold is generated, i.e., the wear indicator time sequence is analyzed to find the time point when the die wear reaches the preset threshold. This time point is the predicted service life of the die, i.e., the time the die is expected to work normally before reaching the unqualified quality state. In this way, the service life of the die can be predicted based on the actual working conditions and performance indicators of the die, thereby realizing quality analysis of the first extrusion die and improving the accuracy of die quality monitoring.

[0054] The specific steps for generating the wear index time series are as follows: first, define the die wear index, define the die wear index to quantify the wear of the die during the extrusion process, these indexes will be used to evaluate the performance of the die and predict its service life. Die wear index can include wear rate, material fatigue, wear degree and other indicators, which can be selected by professionals in the field to reflect the wear of the die, and no restrictions are made.

[0055] Based on the die wear index, a die wear continuous identification module is constructed. The die wear continuous identification module is a machine learning model that can predict wear based on the input target three-way pressure stress distribution characteristics, target billet flow characteristics and first die performance index set, and output the wear index time series. Specifically, professionals in the field can obtain three-way pressure stress distribution characteristic samples, billet flow characteristic samples, die performance index samples and corresponding die wear index samples based on historical die quality monitoring records, and then construct the die wear continuous identification module based on existing machine learning model training. The training of machine learning model is a common technical means for technicians in the field, which is not expanded here. Thus, die wear prediction is achieved, which facilitates the prediction of service life, thereby facilitating die quality monitoring.

[0056] Further, step five of the present application includes:

[0057] Obtain the preset service life of the first extrusion die; determine whether the first predicted service life meets the preset service life; if yes, the quality monitoring verification is passed, if not, the quality monitoring verification is not passed.

[0058] The steps of quality monitoring verification of the first extrusion die based on the first predicted service life are as follows: obtain the preset service life of the first extrusion die, i.e. determine the expected service life of the die under normal working conditions, the preset service life is usually set by the manufacturer or user. Then, compare the first predicted service life with the preset service life. The first predicted service life is the predicted service life of the die based on finite element simulation, wear analysis and other performance evaluation methods. If the first predicted service life meets the preset service life, i.e. the expected service life of the die in actual use is not lower than the standard set by the manufacturer or user, it can be considered that the quality monitoring verification is passed. This indicates that the design and manufacture of the die meet the requirements and can be safely used for production. If the first predicted service life does not meet the preset service life, i.e. the expected service life of the die is lower than the set standard, the quality monitoring verification is not passed. This may indicate that the design, material selection, manufacturing process or use condition of the die needs to be improved. Through this comparison and judgment, the performance of the die can be ensured to meet the predetermined standard, thereby ensuring the continuity of production and the quality of products, thereby achieving precise die quality monitoring and ensuring die production quality.

[0059] In summary, the production and verification method of the metal pipe joint cold extrusion die provided by the application has the following technical effects:

[0060] Obtain a pipe joint extrusion feature group of the first extrusion die, wherein the pipe joint extrusion feature group includes die basic information, target pipe joint geometric structure information, pipe joint material information, and to-be-processed blank basic information; perform finished product quality feature distribution simulation based on the pipe joint extrusion feature group to generate target three-way compressive stress distribution features and target blank flow features; perform initial performance detection on the first extrusion die to generate a first die performance index set; perform die stress resistance analysis on the target three-way compressive stress distribution features, the target blank flow features, and the first die performance index set to generate a first predicted service life; and perform quality monitoring and verification on the first extrusion die based on the first predicted service life. By analyzing the three-way compressive stress distribution and the blank flow features of the first extrusion die during actual extrusion operation, and combining the die performance to predict the service life, quality monitoring is performed, thereby achieving the technical effects of improving the efficiency and accuracy of die quality monitoring.

[0061] The above description of disclosed embodiments enables one of ordinary skill in the art to make or use the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0062] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application also intends to include these modifications and variations.

Claims

1. A method of producing a verification of a cold extrusion die for a metal pipe joint, characterized by, The method comprises: acquiring a pipe joint extrusion feature group of a first extrusion die, wherein the pipe joint extrusion feature group comprises die basic information, target pipe joint geometric structure information, pipe joint material information, and to-be-processed blank basic information; performing finished product quality feature distribution simulation based on the pipe joint extrusion feature group to generate target three-way compressive stress distribution features and target blank flow features; performing initial performance detection on the first extrusion die to generate a first die performance index set; performing die stress resistance analysis on the target three-way compressive stress distribution features, the target blank flow features, and the first die performance index set to generate a first predicted service life; performing quality monitoring verification on the first extrusion die based on the first predicted service life; wherein performing finished product quality feature distribution simulation based on the pipe joint extrusion feature group to generate target three-way compressive stress distribution features and target blank flow features comprises: performing material parameter conversion based on the pipe joint material information to generate a material parameter set; performing finite element modeling with the die basic information, the target pipe joint geometric structure information, the to-be-processed blank basic information, and the material parameter set to generate a first cold extrusion finite element model; constructing a finite boundary condition; driving simulation on the first cold extrusion finite element model with the finite boundary condition and recording three-way compressive stress distribution data set and blank flow feature data set; performing die stress resistance boundary analysis on the three-way compressive stress distribution data set and the blank flow feature data set to generate the target three-way compressive stress distribution features and the target blank flow features; wherein constructing a finite boundary condition comprises: the finite boundary condition comprises die extrusion parameters and extrusion environment; acquiring a preset application scenario of the first extrusion die, retrieving historical extrusion parameters and historical extrusion environment in the preset application scenario to generate extrusion parameter record data set and extrusion environment record data set; performing ladder merging on the extrusion parameter record data set and the extrusion environment record data set to generate a plurality of ladder extrusion parameters and a plurality of ladder extrusion environments; generating the finite boundary condition with the plurality of ladder extrusion parameters and the plurality of ladder extrusion environments; wherein performing die stress resistance boundary analysis on the three-way compressive stress distribution data set and the blank flow feature data set to generate the target three-way compressive stress distribution features and the target blank flow features comprises: performing die resistance loss maximization analysis based on the three-way compressive stress distribution data set to generate the target three-way compressive stress distribution features; performing die resistance loss maximization analysis based on the blank flow feature data set to generate the target blank flow features; wherein performing die resistance loss maximization analysis based on the three-way compressive stress distribution data set to generate the target three-way compressive stress distribution features comprises: performing distributed die stress resistance index identification on the three-way compressive stress distribution data set to generate a die distributed resistance index set; Perform index maximization mapping on the three-directional compressive stress distribution dataset based on the mold distribution adversarial index set to generate the target three-directional compressive stress distribution feature.

2. A method of producing and verifying a metal pipe coupling cold extrusion die according to claim 1, characterized in that, Perform mold stress resistance analysis on the target three-directional compressive stress distribution feature, the target blank flow feature, and the first mold performance index set to generate a first predicted service life, including: Perform continuous mold loss analysis on the target three-directional compressive stress distribution feature, the target blank flow feature, and the first mold performance index set to generate a loss index time sequence. Construct a preset loss index threshold, wherein the preset loss index threshold is the loss index when the mold quality is unqualified. Combine the preset loss index threshold and the loss index time sequence to generate a service life that meets the preset loss index threshold as the first predicted service life.

3. A method of producing and verifying a metal pipe coupling cold extrusion die according to claim 2, characterized in that, Perform continuous mold loss analysis on the target three-directional compressive stress distribution feature, the target blank flow feature, and the first mold performance index set to generate a loss index time sequence, including: Define a mold loss index. Construct a mold loss continuous identification module based on the mold loss index. Perform continuous mold loss analysis on the target three-directional compressive stress distribution feature, the target blank flow feature, and the first mold performance index set using the mold loss continuous identification module to output the loss index time sequence.

4. A method of producing and verifying a metal pipe coupling cold extrusion die according to claim 1, characterized in that, Perform quality monitoring verification on the first extrusion mold based on the first predicted service life, including: Obtain a preset service life of the first extrusion mold. Determine whether the first predicted service life meets the preset service life. If yes, the quality monitoring verification is passed, and if no, the quality monitoring verification is not passed.

Images