Method and System for Monitoring the Service Life of a Forming Die for Powder Metallurgy Metal Materials

Abstract

The present invention discloses a method and system for monitoring the life of a forming die based on powder metallurgy metal materials, comprising: performing multiple fitting and updating on an initial data set consisting of pressing process data and die life change data, obtaining an estimation model for die life change data under normal circumstances, and data sets under normal and extreme circumstances, obtaining an estimation model for die life change data under extreme circumstances based on the pressing process data, duration, and die life change data of a data segment consisting of data points at adjacent moments in the data set under extreme circumstances, and after the forming die to be evaluated completes the current pressing process, obtaining a die life change value based on the pressing process data belonging to normal and extreme circumstances, combined with the estimation model for die life change data, and superimposing it with the die life value after the last pressing process to obtain the die life value after the current pressing process. The present invention can comprehensively and accurately estimate die life changes.

Description

Technical Field

[0001] The present invention relates to the technical field of powder metallurgy, and more particularly to a method and system for monitoring the life of a forming die based on powder metallurgy metal materials. Background Art

[0002] In the production process of powder metallurgy parts, the forming mold is a key process equipment; traditional mold life monitoring methods often rely on regular manual inspections, such as observing the wear of the mold surface and measuring dimensional changes to determine whether the mold needs to be replaced.

[0003] However, this method has obvious limitations: on the one hand, the frequency of manual inspection is usually low, and it is unable to capture subtle changes in the mold during use in a timely manner, which may cause excessive wear of the mold between two inspections and affect product quality; on the other hand, manual inspection is highly subjective, and the judgment results of different inspectors may vary, reducing the accuracy of the inspection.

[0004] Therefore, the mold life prediction method based on data analysis has important practical significance for monitoring the life of molding molds.

[0005] However, the existing mold life prediction model is single and cannot fully reflect the changing laws of mold life under different conditions, and its adaptability and accuracy are limited. Summary of the Invention

[0006] To solve the technical problems that the existing mold life prediction model is single, cannot fully reflect the mold life change law under different situations, and has limited adaptability and accuracy, the present invention provides solutions in the following aspects.

[0007] In the first aspect, the present invention provides a method for monitoring the life of a forming die based on powder metallurgy metal materials, comprising: when a powder metallurgy part is pressed by a forming die, collecting the pressing process data at each moment of each pressing process and the die parameter data after each pressing; performing multi-source data weighted fusion on the die parameter data by the hierarchical analysis method to obtain the die life data after each pressing; forming an initial data set with the pressing process data and the die life change data, performing multiple fitting and updating on the initial data set to obtain an estimation model for the die life change data under normal circumstances, and determining the data set under normal circumstances and the data set under extreme circumstances, and determining the optimal threshold for distinguishing whether the pressing process data belongs to normal circumstances or extreme circumstances by the maximum inter-class variance method; forming data points at adjacent moments in the data set under extreme circumstances into data segments; according to The pressing process data, duration and mold life change data of all data segments in each pressing process are used to construct equations for each pressing process; the equation group composed of the equations of all pressing processes is solved by the least squares method to obtain an estimation model for the mold life change data under extreme conditions; after the molding die to be evaluated completes the current pressing process, the pressing process data belonging to normal conditions and the pressing process data belonging to extreme conditions in all the pressing process data collected during the current pressing process are obtained through the optimal threshold, and are input into the estimation models for the mold life change data under normal conditions and extreme conditions respectively, to obtain the mold life change value of the molding die to be evaluated after the current pressing process, and to superimpose it with the mold life value after the last pressing process to obtain the mold life value of the molding die to be evaluated after the current pressing process.

[0008] Preferably, the pressing process data includes pressing pressure, pressing speed, mold temperature distribution, and mold temperature change rate; the mold parameter data includes: mold deformation data, mold surface roughness data, and mold crack data, wherein the mold deformation data includes dimensional deformation data, parallelism deformation data, and verticality deformation data; the mold crack data includes maximum crack length, maximum crack depth, and number of cracks.

[0009] Preferably, the method for obtaining the initial data set is: calculating the difference between the mold life data after each pressing and the mold life data after the previous pressing as the mold life change data after each pressing; taking the pressing process data as the first dimension and the mold life change data as the second dimension to construct a two-dimensional rectangular coordinate system, then the pressing process data at a moment in a pressing process and the mold life change data after the pressing are completed together constitute a data point in the two-dimensional rectangular coordinate system; and then obtaining the initial data set consisting of all data points based on the pressing process data at all moments in all pressing processes and the mold life change data after all pressing are completed.

[0010] Preferably, the initial data set is fitted and updated multiple times to obtain an estimation model for the mold life change data under normal circumstances, including: taking the pressing process data of the data point as an independent variable, taking the mold life change data of the data point as a dependent variable, constructing an equation based on the pressing process data and the mold life change data of a data point, and recording it as the equation of a data point; fitting the data set by the least squares method; Solve the system of equations consisting of equations for all data points in to obtain The fitting results of the first The fitting results of the calculation data set For each data point in Fitting error; determine the first Outer limits of fitting error; from the data set Delete the data points outside the outer limit and get the data set ;in, The value range is , stop after obtaining the fourth fitting result, and use the fourth fitting result as the estimation model of the pressing process data and the mold life change data under normal conditions, where, When the data set This is the initial data set.

[0011] Preferably, the determining of the data set under normal circumstances and the data set under extreme circumstances includes: As a normal dataset, the initial dataset is compared with the dataset Preferably, the method of determining the optimal threshold value for distinguishing whether the pressing process data belongs to a normal situation or an extreme situation by using the maximum inter-class variance method includes: obtaining the upper quartile of the pressing process data in the normal situation data set. , obtain the lower quartile of the suppression process data in the extreme case data set ; Set the range Each data in is used as a threshold to classify the compression process data of all data points in the initial data set. The compression process data greater than or equal to the threshold are divided into one category, and the compression process data less than the threshold are divided into another category. The inter-class variance of the two categories is calculated; the threshold with the largest inter-class variance is taken as the optimal threshold.

[0012] Preferably, the equations for constructing each pressing process include: for any pressing process, inputting the pressing process data and duration of each data segment in the pressing process into the expression of the model to obtain the simulation value of each data segment; and constructing the equations for each pressing process by making the simulation values of all data segments in the pressing process equal to the mold life change data after the end of the pressing.

[0013] Preferably, the method of obtaining the mold life change value of the molding mold to be evaluated after the current pressing process includes: for any type of pressing process data: inputting each pressing process data belonging to the normal situation into the pressing process data under normal circumstances, and taking the average of the mold life change estimation values corresponding to all the pressing process data belonging to the normal situation as the mold life change estimation value of the current pressing process under normal circumstances; forming a data segment with the pressing process data of adjacent moments in all the pressing process data belonging to the extreme situation, inputting the pressing process data and the duration of each data segment into the estimation model of the mold life change data under extreme circumstances, and taking the sum of the mold life change estimation values corresponding to all the obtained data segments as the mold life change estimation value of the current pressing process under extreme circumstances; taking the maximum value between the mold life change estimation value of the current pressing process under normal circumstances and the mold life change estimation value of the current pressing process under extreme circumstances as the mold life change value corresponding to the pressing process data; and taking the average of the mold life change values corresponding to all the pressing process data as the mold life change value of the molding mold to be evaluated after the current pressing process.

[0014] Preferably, the compression process data of the data segment is equal to the average of the compression process data of all data points in the data segment; the method for obtaining the duration of the data segment is: calculating the product of the number of all compression process data in the data segment and the collection time interval, and summing the product. The ratio of is taken as the duration of the data segment, where Equal to the average duration of all compression processes.

[0015] In a second aspect, the present invention provides a forming die life monitoring system based on powder metallurgy metal materials, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned forming die life monitoring method based on powder metallurgy metal materials is implemented.

[0016] By adopting the above technical solution, the above-mentioned forming die life monitoring method based on powder metallurgy metal materials is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is made based on the memory and the processor for easy use.

[0017] The beneficial effects of the present invention are:

[0018] The present invention combines the influence of the numerical value of the pressing process data under normal conditions on the mold life, and the superimposed influence of the numerical value and duration of the pressing process data under extreme conditions on the mold life, to obtain the optimal threshold value for distinguishing whether the pressing process data belongs to normal conditions or extreme conditions, and solves the estimation model of the mold life change data under normal conditions and extreme conditions; for the forming mold to be evaluated, through classification processing and model calculation, the mold life change is tracked dynamically and in real time, so as to more comprehensively and accurately estimate the mold life change, provide a reliable basis for production decision-making, effectively avoid excessive wear or premature replacement of the mold, reduce production costs, and improve production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0020] Figure 1 It is a flow chart schematically showing the method for monitoring the life of a forming die based on powder metallurgy metal materials in the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0022] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] The embodiment of the present invention discloses a method for monitoring the life of a forming die based on powder metallurgy metal materials, referring to Figure 1 , including steps S1 to S5:

[0024] In the actual production process of powder metallurgy parts pressed by forming dies, data collection mainly involves two types of data, namely pressing process data and die parameter data; among them, the collection of pressing process data is relatively simple and efficient, and can usually be completed synchronously during the pressing process, without significant interference with the normal production process; specifically, by pre-installing sensors on the forming die and related equipment, key data such as pressing pressure, pressing speed, die temperature distribution and die temperature change rate can be collected in real time during each pressing of powder metallurgy parts; these sensors can quickly convert various physical quantities into electrical signals and transmit them to the data acquisition system, thereby realizing dynamic monitoring of the pressing process; this not only ensures the real-time and high efficiency of data collection, but also has no impact on the normal production of powder metallurgy parts, ensuring a balance between production efficiency and data acquisition.

[0025] However, the collection of mold parameter data is completely different. The process is relatively complex and time-consuming, and mainly relies on a variety of precision instruments and testing methods. After each pressing is completed, the mold needs to be removed from the production equipment. Then, using professional equipment such as optical measuring equipment, surface roughness testers and ultrasonic testers, the mold's dimensional deformation (covering deformation indicators such as size, parallelism, and verticality), surface roughness, and crack conditions (including the maximum length, depth, and number of cracks) are meticulously tested. This series of operations not only requires professional testing equipment, but also has high requirements for the testing environment and the technical level of the operators.

[0026] More importantly, since the mold cannot be used for production during the inspection period, this will undoubtedly have a direct impact on the production progress of powder metallurgy parts, increase production waiting time, and reduce overall production efficiency.

[0027] Therefore, although mold parameter data can reflect the mold life more intuitively, from the perspective of production efficiency and cost control, it is expected to estimate the mold life through the pressing process data. By analyzing the pressing process data and mold life data in the test data, a correlation model between the pressing process data and the mold life change data is established, namely, the mold life prediction model.

[0028] S1. Collect the life test data of the molding die. The test data includes the pressing process data and the die parameter data. The die parameter data is weightedly fused with multi-source data through the hierarchical analysis method to obtain the die life data after each pressing.

[0029] It should be noted that the hierarchical analysis method is first used to perform multi-source data weighted fusion on the mold parameter data of each molding mold after each pressing in the life test data to obtain the mold life data of each molding mold after each pressing. This provides strong data support for the subsequent analysis of the pressing process data and mold life data in the test data, and the establishment of a correlation model between the pressing process data and the mold life change data, namely the mold life prediction model.

[0030] Specifically, powder metallurgy parts are pressed by forming dies, and in each process of pressing the powder metallurgy parts by the forming dies, the pressing process data at each moment of each pressing process is collected; after each time the powder metallurgy parts are pressed by the forming dies, the mold parameter data after each pressing is collected; the pressing process data at each moment of each pressing process and the mold parameter data after each pressing are used as the life test data of each forming die in each pressing process; the mold parameter data of each forming die after each pressing is completed are subjected to multi-source data weighted fusion through the hierarchical analysis method to obtain the mold life data of each forming die after each pressing, thereby realizing the life test of each forming die.

[0031] The pressing process data includes pressing pressure, pressing speed, mold temperature distribution, and mold temperature change rate. The collection method of each pressing process data and its impact on the life of the forming mold are as follows:

[0032] (1) Regarding the pressing pressure, high-precision pressure sensors are installed at key positions of the pressure system of the powder metallurgy molding machine to sense the pressure during pressing in real time. After being processed by the signal conversion and acquisition equipment, they are transmitted to the data acquisition system, which can obtain continuous and accurate pressure data during the pressing process. Excessive pressure will cause local stress concentration in the molding die, accelerate the wear and deformation of the molding die, and affect its service life.

[0033] (2) Regarding the pressing speed, laser displacement sensors are installed at key positions of the transmission system of the powder metallurgy molding machine to monitor the displacement changes of the pressing head in real time and calculate the speed. Both of them transmit the speed data to the data acquisition system. In addition, a pressing speed that is too fast will cause the molding die to be subjected to a greater impact force, increase the wear and fatigue damage of the molding die, and thus affect its life.

[0034] (3) Regarding the mold temperature distribution, the temperature data of the molding mold is collected non-contactly by using an infrared thermometer, and the temperature data is transmitted to the data acquisition system in real time to achieve multi-point, real-time temperature monitoring; the range and variance of the temperature data at all positions of the molding mold are calculated, and the product of the range and variance is used as the mold temperature distribution; uneven temperature distribution will lead to uneven thermal expansion of the molding mold, generate thermal stress, and then cause deformation, cracking and other problems of the molding mold, affecting its life.

[0035] (4) Regarding the mold temperature change rate, the mold temperature change rate refers to the ratio of the difference in the temperature data of the molding mold at adjacent moments to the time interval between adjacent moments, which can reflect the dynamic change characteristics of the molding mold temperature; excessively rapid temperature changes will cause the molding mold to be subjected to thermal shock, resulting in cracks on the surface and inside of the molding mold, and reducing the service life of the molding mold.

[0036] The mold parameter data includes mold deformation data, mold surface roughness data, and mold crack data. The mold deformation data includes dimensional deformation data, parallelism deformation data, and perpendicularity deformation data. The mold crack data includes the maximum crack length, the maximum crack depth, and the number of cracks. The mold parameter data includes dimensional deformation data, parallelism deformation data, perpendicularity deformation data, mold surface roughness data, the maximum crack length, the maximum crack depth, and the number of cracks. The collection method of each mold parameter data is as follows:

[0037] (1) For the mold deformation data, use a three-dimensional measuring machine or optical measuring equipment to measure the size, parallelism and verticality of the forming mold; measure the unused forming mold to obtain the initial size, initial parallelism and initial verticality of the forming mold; measure the forming mold after each pressing to obtain the size, parallelism and verticality of the forming mold after each pressing; calculate the absolute value of the difference between the size, parallelism and verticality of the forming mold after each pressing and the initial size, initial parallelism and initial verticality of the forming mold, and obtain the size deformation data, parallelism deformation data and verticality deformation data of the forming mold after each pressing.

[0038] (2) For the surface roughness data of the mold, a surface roughness measuring instrument is used to detect the roughness value of the surface of the molding mold after each pressing, and the surface roughness data of the molding mold after each pressing is obtained.

[0039] (3) Based on the mold crack data, non-destructive testing methods such as ultrasonic testing, magnetic particle testing or penetration testing are used to conduct a comprehensive crack detection on the molding mold after each pressing. For all cracks found, their length and depth are recorded, and the maximum value of all crack lengths is taken as the maximum crack length, and the maximum value of all crack depths is taken as the maximum crack depth.

[0040] Among them, the multi-source data weighted fusion is performed on the mold parameter data of each molding mold after each pressing by the hierarchical analysis method to obtain the mold life data of each molding mold after each pressing, including:

[0041] (1) A hierarchical model is established. The hierarchical model consists of three levels, namely, the target layer, the criterion layer, and the indicator layer. The target layer is the expected result of the problem. In this embodiment, the mold life assessment is taken as the target layer. The criterion layer includes the main factors that affect the realization of the goal. In this embodiment, the mold deformation, mold surface roughness, and mold crack are taken as the criterion layer. The indicator layer is a specific refinement of the criterion layer factors. In this embodiment, the mold deformation corresponds to the dimensional deformation data, the parallelism deformation data, and the perpendicularity deformation data, the mold surface roughness corresponds to the mold surface roughness data, and the mold crack corresponds to the maximum crack length, the maximum crack depth, and the number of cracks.

[0042] (2) Constructing a judgment matrix: Through expert scoring, the factors at the criterion layer and the indicator layer are compared pairwise, assigned scales, and the comparison results are quantified using a 1-9 scale method, where 1 means that both are equally important, 3 means that one is slightly more important, 5 means that one is obviously more important, 7 means that one is very important, 9 means that one is absolutely important, and 2, 4, 6, and 8 are intermediate values. Construct a judgment matrix to determine the relative importance of each factor.

[0043] (3) Calculating the weight vector, including: normalizing the judgment matrix to obtain the weight vector of each factor.

[0044] (4) Perform hierarchical single sorting and hierarchical total sorting, including: hierarchical single sorting refers to calculating the weight vector for each judgment matrix to obtain the ranking of each factor at this level relative to a factor at the previous level; hierarchical total sorting refers to calculating the total ranking weight of each factor relative to the target level by integrating the single sorting results of each level, thereby obtaining the final weight of each factor.

[0045] (5) Using the parameter data of each mold and its weight, the data fusion is completed through the weighted average method to obtain the mold life data after each pressing.

[0046] It should be noted that the analytic hierarchy process is a multi-criteria decision analysis method that combines qualitative and quantitative methods, which can help determine the weight of each data. The analytic hierarchy process is a well-known technology and will not be described in detail here.

[0047] S2. The pressing process data and the mold life change data constitute an initial data set, and the initial data set is fitted and updated multiple times to obtain an estimation model of the mold life change data under normal circumstances, and determine the data set under normal circumstances and the data set under extreme circumstances.

[0048] It should be noted that the life test data of the molding mold includes pressing process data belonging to normal conditions and pressing process data belonging to extreme conditions: for the pressing process data belonging to normal conditions, the degree of influence on the mold life changes with the change of the numerical value, and for the pressing process data belonging to extreme conditions, the degree of influence on the mold life is not only related to the numerical value, but also superimposed with the duration of the extreme condition; therefore, the influence of the pressing process data belonging to extreme conditions on the mold life is different from the influence of the pressing process data belonging to normal conditions on the mold life, so this embodiment performs multiple fitting and updates on the initial data set composed of the pressing process data and the mold life change data, and deletes the pressing process data belonging to extreme conditions from the initial data set by continuously updating the initial data set, retaining only the data set composed of the pressing process data under normal conditions, and obtaining an estimation model for the mold life change data under normal conditions by fitting the data set composed of the pressing process data under normal conditions.

[0049] Specifically, the difference between the mold life data after each pressing and the mold life data after the previous pressing is calculated as the mold life change data after each pressing. For any pressing process data: the pressing process data and the mold life change data constitute an initial data set, and the initial data set is fitted and updated multiple times to obtain an estimation model for the mold life change data under normal conditions, and determine the data set under normal conditions and the data set under extreme conditions. The specific process is as follows:

[0050] 1. Take the pressing process data as the first dimension and the mold life change data as the second dimension to construct a two-dimensional rectangular coordinate system. The pressing process data at a moment in a pressing process and the mold life change data after the pressing process are completed constitute a data point in the two-dimensional rectangular coordinate system. Then, based on the pressing process data at all moments in all pressing processes and the mold life change data after all pressing processes, the initial data set consisting of all data points is obtained and recorded as the data set. .

[0051] 2. Take the pressing process data of the data point as the independent variable and the mold life change data of the data point as the dependent variable. According to the pressing process data and mold life change data of a data point, construct an equation and record it as the equation of a data point; use the least squares method to calculate the data set. Solve the equations composed of the equations of all data points in to obtain the first fitting result; based on the first fitting result, calculate the data set The first fitting error of each data point in the dataset is obtained; the outer limit of the first fitting error of all data points is determined by box plot; Delete the data points outside the outer limit and get the data set .

[0052] Among them, when fitting, linear fitting, quadratic fitting and cubic fitting are performed respectively, that is, a linear equation, a quadratic equation and a cubic equation are constructed respectively. After obtaining fitting results of different orders, the fitting effect is evaluated by residual analysis: if the residuals are randomly distributed near zero, it means that the fitting result is good; if the residuals show a systematic trend, it is necessary to try a higher order fitting.

[0053] 3. Take the pressing process data of the data point as the independent variable and the mold life change data of the data point as the dependent variable. According to the pressing process data and mold life change data of a data point, construct an equation and record it as the equation of a data point; use the least squares method to calculate the data set. Solve the equations composed of the equations of all data points in to obtain the second fitting result; based on the second fitting result, calculate the data set The second fitting error of each data point in the dataset is obtained; the outer limit of the second fitting error of all data points is determined by box plot; Delete the data points outside the outer limit and get the data set .

[0054] 4. Take the pressing process data of the data point as the independent variable and the mold life change data of the data point as the dependent variable. According to the pressing process data and mold life change data of a data point, construct an equation and record it as the equation of a data point; use the least squares method to calculate the data set. Solve the equations composed of the equations of all data points in to obtain the third fitting result; based on the third fitting result, calculate the data set The third fitting error of each data point in the dataset is obtained; the outer limit of the third fitting error of all data points is determined by box plot; Delete the data points outside the outer limit and get the data set .

[0055] 5. Take the pressing process data of the data point as the independent variable and the mold life change data of the data point as the dependent variable, and use the least squares method to calculate the data set. Perform the fourth linear fitting on all the data points in , and obtain the fourth fitting result, which is used as the estimation model of the pressing process data and the mold life change data under normal circumstances.

[0056] It should be noted that when performing the second to fourth linear fitting, the number of fitting results is the same as the number of fitting results obtained by the first linear fitting.

[0057] 6. Dataset As a normal dataset, the initial dataset is compared with the dataset The difference of , as the data set in the extreme case.

[0058] S3. Based on the data sets under normal conditions and the data sets under extreme conditions, the optimal threshold for distinguishing whether the suppression process data belongs to normal conditions or extreme conditions is determined by using the maximum inter-class variance method.

[0059] It should be noted that in order to find a boundary that can effectively distinguish between normal and extreme situations in the pressing process data, this embodiment uses the maximum inter-class variance method to determine the optimal threshold based on the statistical characteristics of the data, which can maximize the difference between the classified normal and extreme situation data, thereby improving the accuracy of classification.

[0060] Specifically, for any type of suppression process data: based on the data set under normal conditions and the data set under extreme conditions, the maximum inter-class variance method is used to determine the optimal threshold for distinguishing whether the suppression process data belongs to normal conditions or extreme conditions. The specific process is:

[0061] 1. Obtain the upper quartile of the suppression process data in the data set under normal conditions , obtain the lower quartile of the suppression process data in the extreme case data set .

[0062] The upper quartile and lower quartile refer to the values at the 25% and 75% positions after sorting a set of data from small to large.

[0063] 2. Set the scope Each data in is used as a threshold to classify the compression process data of all data points in the initial data set. The compression process data greater than or equal to the threshold are divided into one category, and the compression process data less than the threshold are divided into another category. The inter-class variance of the two categories is calculated; the threshold with the largest inter-class variance is used as the optimal threshold to distinguish whether the compression process data belongs to normal or extreme conditions.

[0064] It should be noted that by determining the optimal threshold, normal data and extreme data in the suppression process can be identified more accurately, providing a reliable data classification basis for the subsequent construction of prediction models and life prediction, thereby improving the credibility of the prediction results.

[0065] S4. Obtain an estimation model for mold life change data under extreme conditions based on the pressing process data, duration, and mold life change data of a data segment composed of data points at adjacent moments in the data set under extreme conditions.

[0066] It should be noted that, for the pressing process data belonging to extreme cases, the degree of impact on the mold life is not only related to the numerical value, but also superimposed with the duration of the extreme case. Therefore, this embodiment organizes the data points at adjacent moments in the data set under extreme cases into data segments, and the mold life change data after one pressing is equal to the cumulative amount of the mold life change evaluation values corresponding to all data segments in one pressing process. Accordingly, according to the pressing process data, duration and mold life change data of all data segments in each pressing process, the equations of each pressing process are constructed, and the system of equations composed of the equations of all pressing processes is solved by the least squares method to obtain an estimation model for the mold life change data under extreme cases.

[0067] Specifically, for any pressing process data, the data points at adjacent moments in the data set under extreme conditions are grouped into data segments. Based on the pressing process data, duration, and mold life change data after the pressing process in all data segments of each pressing process, equations for each pressing process are constructed. The system of equations composed of all pressing process equations is solved using the least squares method to obtain an estimation model for mold life change data under extreme conditions. The specific process is as follows:

[0068] 1. For all data points in the data set in extreme cases, divide all data points into multiple data segments according to the compression process and time corresponding to the data points. It is required that the compression process corresponding to all data points in each data segment is the same, and the time corresponding to all data points in each data segment is continuous.

[0069] For example, when the dataset in the extreme case is When, among them, Indicates the During the first pressing process The pressing process data at the moment and the The data points composed of the mold life change data after the first pressing are The data point represents the pressing process data at the 18th moment in the first pressing process and the mold life change data after the first pressing. According to the pressing process and time corresponding to the data point, all data points are divided into multiple data segments, and a total of 4 data segments are obtained, namely 、 、 、 .

[0070] 2. For any data segment, calculate the mean of the compression process data of all data points in the data segment as the compression process data of the data segment; calculate the product of the number of all compression process data in the data segment and the collection time interval, and sum the product with The ratio of is taken as the duration of the data segment, where It is equal to the average duration of all compression processes and is used to normalize the duration of the data segment.

[0071] 3. Take the pressing process data and duration of the data segment as independent variables, and the mold life change data as the dependent variable. For any pressing process: according to the pressing process data, duration of all data segments in the pressing process, and the mold life change data after the pressing is completed, input the pressing process data and duration of each data segment in the pressing process into the model expression to obtain the simulation value of each data segment; by making the simulation value of all data segments in the pressing process equal to the mold life change data after the pressing is completed, construct the equation for each pressing process, specifically:

[0072] ;

[0073] Where, This is the first Suppression process data of data segments, This is the first The duration of a data segment, is the expression of the model, is the number of all data segments in the compression process, This is the mold life change data after the pressing is completed.

[0074] 4. Solve the system of equations consisting of all pressing process equations using the least squares method to obtain an estimation model for the pressing process data and mold life change data under extreme conditions.

[0075] Among them, when fitting, binary linear fitting, binary quadratic fitting, binary cubic fitting and binary quartic fitting are performed respectively, that is, binary linear equations, binary quadratic equations, binary cubic equations and binary quartic equations are constructed respectively. After obtaining the fitting results of models of different orders, the fitting effect of the model is evaluated by residual analysis: if the residuals are randomly distributed near zero, it means that the fitting effect of the model is good; if the residuals show a systematic trend, it is necessary to try a higher-order model.

[0076] It should be noted that based on the continuity and correlation of data under extreme conditions, by constructing a set of equations and solving them, a mold life change prediction model specifically for extreme conditions can be established, which makes up for the prediction deviation that may be caused by using only the normal condition model and improves the prediction ability of mold life under various complex conditions.

[0077] S5. After the molding die to be evaluated completes the current pressing process, the mold life change value is obtained based on the pressing process data belonging to normal and extreme conditions, combined with the estimation model of the mold life change data, and the mold life change value is superimposed on the mold life value after the last pressing process to obtain the mold life value after the current pressing process.

[0078] It should be noted that this embodiment applies the previously established prediction model to the actual mold life prediction process. Through classification processing and model calculation, the changes in mold life can be tracked dynamically and in real time.

[0079] Specifically, for the molding die to be evaluated, the powder metallurgy part is pressed by the molding die to be evaluated. During the current pressing of the powder metallurgy part by the molding die to be evaluated, pressing process data at each moment of each pressing process is collected.

[0080] Furthermore, after the powder metallurgy part is pressed by the molding die to be evaluated for the current time, for any pressing process data: the optimal threshold is used to obtain the pressing process data belonging to normal conditions and the pressing process data belonging to extreme conditions from all the pressing process data collected during the current pressing process, and the data are respectively input into the estimation model of the mold life change data under normal conditions and extreme conditions to obtain the mold life change value corresponding to the pressing process data. The specific process is as follows:

[0081] 1. Through the optimal threshold, obtain the pressing process data belonging to normal conditions and the pressing process data belonging to extreme conditions among all the pressing process data collected in the current pressing process: if the pressing process data is less than the optimal threshold, then the pressing process data belongs to normal conditions; if the pressing process data is greater than or equal to the optimal threshold, then the pressing process data belongs to extreme conditions.

[0082] 2. Input each pressing process data belonging to normal conditions among all the pressing process data collected in the current pressing process into the pressing process data under normal conditions to obtain the estimated value of the mold life change corresponding to each pressing process data belonging to normal conditions; calculate the average of the estimated value of the mold life change corresponding to all the pressing process data belonging to normal conditions as the estimated value of the mold life change of the current pressing process under normal conditions.

[0083] 3. Divide all the pressing process data that belong to extreme cases in all the pressing process data collected during the current pressing process into multiple data segments. It is required that the time corresponding to all data points in each data segment is continuous, and the data segment is recorded as a data segment belonging to extreme cases; calculate the mean of the pressing process data of all data points in each data segment as the pressing process data of each data segment; calculate the product of the number of all pressing process data in each data segment and the collection time interval, and sum the product with The ratio of is taken as the duration of each data segment.

[0084] 4. Input the pressing process data and duration of each data segment belonging to the extreme case into the estimation model of the mold life change data under extreme cases to obtain the estimated value of the mold life change corresponding to each data segment belonging to the extreme case; calculate the sum of the estimated values of the mold life change corresponding to all data segments belonging to the extreme case as the estimated value of the mold life change of the current pressing process under extreme cases.

[0085] 5. The maximum value of the estimated value of the mold life change in the current pressing process under normal circumstances and the estimated value of the mold life change in the current pressing process under extreme circumstances is used as the mold life change value corresponding to the pressing process data.

[0086] Finally, the average of the mold life change values corresponding to all pressing process data is used as the mold life change value of the molding mold to be evaluated after the current pressing process; the mold life change value of the molding mold to be evaluated after the current pressing process is superimposed with the mold life value after the last pressing process to obtain the mold life value of the molding mold to be evaluated after the current pressing process.

[0087] It should be noted that through real-time and accurate prediction of the life of molding molds, production personnel can make timely decisions based on the prediction results, such as arranging mold maintenance or replacement in advance, effectively avoiding production quality problems and production interruption risks caused by excessive mold wear, improving production efficiency and product quality, and also reducing production costs.

[0088] An embodiment of the present invention also discloses a forming die life monitoring system based on powder metallurgy metal materials, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a forming die life monitoring method based on powder metallurgy metal materials according to the present invention is implemented.

[0089] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

Claims

1. A method for monitoring the life of a forming die based on powder metallurgy metal materials, characterized in that: include: When powder metallurgy parts are pressed by forming dies, the pressing process data at each moment of each pressing process and the die parameter data after each pressing are collected; the die parameter data are weightedly fused from multiple sources using the analytic hierarchy process to obtain the die life data after each pressing. Calculate the difference between the mold life data after each pressing and the mold life data after the previous pressing as the mold life change data after each pressing; use the pressing process data and the mold life change data as two dimensions to construct a two-dimensional rectangular coordinate system, so that the pressing process data at a moment in a pressing process and the mold life change data after the pressing are completed together constitute a data point in the two-dimensional rectangular coordinate system; then obtain the initial data set composed of all data points based on the pressing process data at all moments in all pressing processes and the mold life change data after all pressing are completed; use the pressing process data and the mold life change data of the data point as the independent variable and the dependent variable, respectively, and construct an equation for a data point based on the pressing process data and the mold life change data of a data point; use the least squares method to calculate the data set. Solve the system of equations consisting of equations for all data points in to obtain The fitting results of the first The fitting results of the calculation data set For each data point in Fitting error; determine the first Outer limits of fitting error; from the data set Delete the data points outside the outer limit and get the data set ; The value range is , stop after obtaining the fourth fitting result, and use the fourth fitting result as the estimation model of the pressing process data and the mold life change data under normal circumstances, and When the data set It is the initial data set; And determine the data set under normal conditions and the data set under extreme conditions; obtain the upper quartile of the suppression process data in the data set under normal conditions and the lower quartile of the suppression process data in the extreme case data set ; Set the range Each data in is used as a threshold to classify the compression process data of all data points in the initial data set. The compression process data greater than or equal to the threshold are divided into one category, and the compression process data less than the threshold are divided into another category. The inter-class variance of the two categories is calculated; the threshold with the largest inter-class variance is taken as the optimal threshold; Data points at adjacent moments in the extreme case data set are grouped into data segments; equations for each pressing process are constructed based on the pressing process data, duration, and mold life change data after the pressing process in all data segments of each pressing process; the system of equations consisting of the equations for all pressing processes is solved using the least squares method to obtain an estimation model for mold life change data under extreme cases; After the molding die to be evaluated completes the current pressing process, the pressing process data belonging to normal conditions and the pressing process data belonging to extreme conditions are obtained from all the pressing process data collected during the current pressing process through the optimal threshold; for any pressing process data: each pressing process data belonging to the normal condition is input into the pressing process data under normal conditions, and the average of the estimated values of the mold life change corresponding to all the pressing process data belonging to the normal condition is used as the estimated value of the mold life change of the current pressing process under normal conditions; the pressing process data at adjacent moments in all the pressing process data belonging to the extreme conditions are grouped into data segments, and the pressing process data of each data segment are grouped into The data and duration are input into the estimation model of the mold life change data under extreme conditions, and the sum of the mold life change estimation values corresponding to all the obtained data segments is used as the mold life change estimation value of the current pressing process under extreme conditions; the maximum value of the mold life change estimation values of the current pressing process under normal conditions and extreme conditions is used as the mold life change value corresponding to the pressing process data; the average of the mold life change values corresponding to all the pressing process data is used as the mold life change value of the molding mold to be evaluated after the current pressing process; and it is superimposed with the mold life value after the last pressing process to obtain the mold life value of the molding mold to be evaluated after the current pressing process.

2. The method for monitoring the life of a forming die based on powder metallurgy metal materials according to claim 1, characterized in that: The pressing process data includes pressing pressure, pressing speed, mold temperature distribution, and mold temperature change rate; the mold parameter data includes: mold deformation data, mold surface roughness data, and mold crack data, wherein the mold deformation data includes dimensional deformation data, parallelism deformation data, and verticality deformation data; the mold crack data includes maximum crack length, maximum crack depth, and number of cracks.

3. The method for monitoring the life of a forming die based on powder metallurgy metal materials according to claim 1, characterized in that: Determining the data set under normal circumstances and the data set under extreme circumstances includes: The dataset As a normal dataset, the initial dataset is compared with the dataset The difference of , as the data set in the extreme case.

4. The method for monitoring the life of a forming die based on powder metallurgy metal materials according to claim 1, characterized in that: The equations for constructing each pressing process include: For any pressing process, the pressing process data and duration of each data segment in the pressing process are input into the model expression to obtain the simulation value of each data segment; The equations for each pressing process are constructed by assuming that the simulated values of all data segments during the pressing process are equal to the mold life change data after the pressing is completed.

5. The method for monitoring the life of a forming die based on powder metallurgy metal materials according to claim 1, characterized in that: The compression process data of the data segment is equal to the average of the compression process data of all data points in the data segment; the method for obtaining the duration of the data segment is: calculating the product of the number of all compression process data in the data segment and the collection time interval, and multiplying the product by The ratio of is taken as the duration of the data segment, where Equal to the average duration of all compression processes.

6. The forming die life monitoring system based on powder metallurgy metal materials is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the forming die life monitoring method based on powder metallurgy metal materials according to any one of claims 1 to 5 is implemented.

Images