Optimization method and device for metal powder injection molding process parameters

By optimizing the process parameters of metal powder injection molding and using neural networks to adjust the process parameters, the limitations of traditional metal processing technology in manufacturing complex-shaped metal ornaments have been overcome, achieving high-precision molding at high efficiency and low cost.

CN119007880APending Publication Date: 2024-11-22SUIZHOU HAIFUTE HARDWARE CO LTD

Patent Information

Application Number
CN202410863228.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-29
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Traditional metal processing techniques have limitations in manufacturing complex shapes, high precision, miniaturized, and mass-produced metal ornaments, and inaccurate process parameters lead to high production costs and low efficiency.

Method used

Metal powder injection molding technology is used. By setting prediction parameters and a trained neural network, the process parameters are optimized, including the content of additional components, target hardness value, target tensile strength value and process parameters. JMatPro software is used to predict the component ratio, and the process parameters are adjusted by a BP neural network to optimize the molding process.

Benefits of technology

It improves the hardness and tensile strength of metal ornaments, reduces shrinkage, increases production efficiency, and lowers costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007880A_ABST
    Figure CN119007880A_ABST
Patent Text Reader

Abstract

The invention provides a metal powder injection molding process parameter optimization method and device, and the method comprises the steps: setting prediction parameters which comprise the content of additional components, a hardness target value, a tensile strength target value and a process parameter, the preset range is determined based on JMatPro, the content of each component in the metal powder, a hardness target value, a tensile strength target value and a preset upper limit value; prediction parameters are input based on a trained neural network, a shrinkage rate prediction value is obtained, and the neural network is obtained through training based on production data of different products; judging whether the predicted value of the shrinkage rate is lower than a target value of the shrinkage rate; if so, adjusting process parameters based on a preset rule; and if not, judging that the process parameters reach the standard. The invention provides an optimization method and device for metal powder injection molding process parameters. The optimization method and device are used for providing accurate composition proportion and reasonably optimized process parameters.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of metal powder injection molding, and in particular to a method and a device for optimizing process parameters of metal powder injection molding. Background Art

[0002] With the development of society and the improvement of people's living standards, the market demand for metal decorations has increased year by year. Consumers have put forward higher requirements on the style, quality, cost and other aspects of metal decorations. Traditional metal processing technologies, such as casting, forging, machining, etc., have certain limitations in manufacturing complex shapes, high precision, miniaturization and batch production of metal decorations. Metal powder injection molding (MIM), as the fastest-growing and most promising near-net forming technology in the field of new material forming in the world in recent years, has been widely used in the field of forming parts with small and complex structures. Metal powder injection molding technology can directly obtain the final required shape parts without the need for subsequent machining steps, and has a high degree of freedom in shape design. At the same time, the product material system is extensive, the organization is uniform, the performance is excellent, and the material utilization rate is high. Metal powder injection molding technology provides an efficient, high-precision, and low-cost solution for the manufacture of metal decorations, which has high research value and market application prospects.

[0003] Metal powder injection molding process flow Figure 1 As shown in the figure, it mainly includes four process steps: granulation, injection molding, degreasing, and sintering. The metal powder and binder are mixed and then granulated, which is called feeding. For metal accessories, they must undergo heat treatment, coating, polishing, laser engraving and other processes to achieve the performance requirements and appearance of the final product. Granulation, injection molding, degreasing, sintering and other processes have a huge impact on the performance of the final metal accessories. Therefore, accurate component ratios and reasonably optimized process parameters are of great significance to improving the performance of metal accessories, reducing production costs, and improving production efficiency. Summary of the invention

[0004] The invention provides a method and device for optimizing process parameters of metal powder injection molding, which are used to provide accurate component ratio and reasonably optimized process parameters.

[0005] In a first aspect, the present invention provides a method for optimizing process parameters of metal powder injection molding, comprising:

[0006] Step 101, setting prediction parameters, the prediction parameters include additional component content, hardness target value, tensile strength target value and process parameters, the additional component is used to be added to the metal powder to improve the hardness and tensile strength, the additional component content is within a preset range, the preset range is determined based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and a preset upper limit value, the process parameters include injection speed, injection pressure, holding time and sintering temperature, and the process parameters are within the process parameter range;

[0007] Step 102: input the prediction parameters based on the trained neural network to obtain a predicted shrinkage value, wherein the neural network is trained based on production data of different products, and the different products are obtained by actual production tests based on the metal powder, the additional components, the preset range and the process parameter range, and the production data includes the additional component content, hardness test value, tensile strength test value, process parameters and shrinkage test value;

[0008] Step 103, determining whether the predicted shrinkage rate value is greater than the target shrinkage rate value, if so, executing step 104, otherwise executing step 105;

[0009] Step 104: adjusting the process parameters based on preset rules, and executing steps 101 to 103 for the adjusted process parameters;

[0010] Step 105: Determine whether the process parameters meet the standards.

[0011] In the above scheme, based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and the preset upper limit value to determine the preset range of the additional component, a more accurate and reliable composition ratio of the metal powder can be obtained, thereby improving the rheological properties of the feed; at the same time, by optimizing the process parameters that match the composition ratio, not only the hardness and tensile strength of the metal accessories are improved, but also the shrinkage rate is reduced.

[0012] Optionally, the preset range is determined based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and the preset upper limit value, and includes the following steps:

[0013] Step 201, obtaining a hardness prediction value and a tensile strength prediction value based on JMatPro and the content of each component in the metal powder;

[0014] Step 202, judging whether the predicted hardness value is greater than or equal to the target hardness value and whether the predicted tensile strength value is greater than or equal to the target tensile strength value, if not, executing step 203, otherwise executing step 204;

[0015] Step 203, adding the additional component according to a preset step length, and executing steps 201 to 202 for the metal powder after adding the additional component;

[0016] Step 204, taking the current additional component content as the predicted lower limit value, and executing step 205;

[0017] Step 205, continue to add the additional component according to the preset step length, and determine whether the current additional component content is greater than the preset upper limit value. If so, execute step 206, otherwise execute step 207;

[0018] Step 206, taking the difference between the current additional component content and the preset step length as the prediction upper limit value, and executing step 209;

[0019] Step 207, for the metal powder after the additional component is added, first perform step 201 and then perform step 208;

[0020] Step 208, determining whether the predicted hardness value is greater than or equal to the target hardness value and whether the predicted tensile strength value is greater than or equal to the target tensile strength value, if yes, executing step 205, otherwise executing step 206;

[0021] Step 209: Determine the preset range according to the prediction lower limit value and the prediction upper limit value.

[0022] Optionally, the neural network is a BP neural network, including an input layer, a hidden layer and an output layer.

[0023] Optionally, the neural network is trained based on production data of different products and includes:

[0024] Arrange the production data of the different products into data sets and perform normalization processing;

[0025] The normalized data set is divided into a training set and a test set in a ratio of 8:2 to train the neural network.

[0026] Optionally, the different products are obtained by conducting actual production tests based on the metal powder, the additional components, the preset range and the process parameter range, including:

[0027] Setting different production plans according to the preset range and the process parameter range, the production plans including the content of the additional component and the process parameters;

[0028] The different products are obtained by carrying out actual production tests based on the metal powder and the additional components according to the different production plans.

[0029] Optionally, the hardness test value, the tensile strength test value and the shrinkage test value are obtained based on the product test.

[0030] Optionally, the preset rule is determined in the following manner:

[0031] Selecting one of the process parameters from the prediction parameters in turn as a variable;

[0032] Inputting the prediction parameters corresponding to different values ​​of the variables into the neural network to obtain the predicted values ​​of the shrinkage rate;

[0033] The proportional relationship between the variable and the shrinkage rate is determined based on each value of the variable and the corresponding predicted shrinkage rate value.

[0034] In a second aspect, the present invention provides a device for optimizing process parameters of metal powder injection molding, comprising:

[0035] A setting module, used to set prediction parameters, the prediction parameters include additional component content, hardness target value, tensile strength target value and process parameters, the additional component is used to be added to the metal powder to improve the hardness and tensile strength, the additional component content is within a preset range, the preset range is determined based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and a preset upper limit value, the process parameters include injection speed, injection pressure, holding time and sintering temperature, and the process parameters are within the process parameter range;

[0036] A prediction module, for inputting the prediction parameters based on a trained neural network to obtain a predicted value of shrinkage, wherein the neural network is trained based on production data of different products, and the different products are obtained by actual production tests based on the metal powder, the additional components, the preset range and the process parameter range, and the production data includes the content of the additional components, the hardness test value, the tensile strength test value, the process parameters and the shrinkage test value;

[0037] A judgment module, used to judge whether the predicted shrinkage rate value is greater than the target shrinkage rate value;

[0038] an adjustment module, configured to adjust the process parameters based on preset rules when the result of the judgment module is yes, and input the adjusted process parameters into the setting module;

[0039] The determination module is used to determine that the process parameters meet the standards when the result of the determination module is no.

[0040] In a third aspect, the present invention provides a computing device, comprising:

[0041] A memory for storing program instructions;

[0042] The processor is used to call the program instructions stored in the memory and execute any of the above methods according to the obtained program.

[0043] In a fourth aspect, the present invention provides a computer-readable non-volatile storage medium, comprising computer-readable instructions, which enables the computer to execute any of the above methods when the computer reads and executes the computer-readable instructions. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of a metal powder injection molding process provided as background technology of the present invention;

[0046] Figure 2 A schematic flow chart of a method for optimizing process parameters of metal powder injection molding provided by an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of outputting a hardness prediction value and a tensile strength prediction value provided by an embodiment of the present invention;

[0048] Figure 4 A schematic diagram of the structure of a BP neural network provided in an embodiment of the present invention;

[0049] Figure 5 The shrinkage ratio provided in the embodiments of the present invention is proportional to the injection speed, injection pressure, holding time and sintering temperature;

[0050] Figure 6 A schematic structural diagram of a device for optimizing process parameters of metal powder injection molding provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] Figure 2A schematic flow chart of a method for optimizing process parameters of metal powder injection molding provided by an embodiment of the present invention is shown in detail, including:

[0053] Step 101, setting prediction parameters, which include additional component content, hardness target value, tensile strength target value and process parameters.

[0054] Specifically, the additional component is used to be added to the metal powder to improve the hardness and tensile strength. The additional component may be a component already present in the metal powder or another component other than the existing components of the metal powder.

[0055] The more common additional components in metal alloying treatment include C, N, Si, Cr, Ni, Ti, Nb, Mo, W, V and some rare earth elements. For example, Ni and Cr are integrated into the lattice of the metal matrix, disrupting the lattice arrangement order and hindering the movement of dislocations, thereby improving the hardness and tensile strength of the product; elements such as W, V, Nb combine with C and N to form hard carbides or nitrides. The formed compounds will improve the hardness and wear resistance of the product, and can also prevent the growth of grains, thereby refining the grains and increasing the number of grain boundaries; rare earth elements can improve the original grain boundary characteristics, hinder grain boundary migration, thereby strengthening the grain boundary and improving the toughness and fatigue life of the product.

[0056] It should be noted that the present invention is applicable to both metal powders containing only metal components and metal powders containing a small amount of non-metallic components (such as C, Si, etc.).

[0057] In one example, considering factors such as raw material cost, equipment production conditions, and waste collection, Ti is selected as an additional component. The method of adding Ti is as follows: when the feed is heated to a molten state, a certain amount of Ti is injected into the mold cavity under the pressure of the injection molding machine for mixing and stirring.

[0058] Specifically, the content of the additional component is within a preset range, and the preset range is determined based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and a preset upper limit value.

[0059] The preset range will serve as a control parameter in the manufacturing process to ensure the consistency and reliability of product performance.

[0060] In one example, the preset range is determined as follows:

[0061] Step 201, obtaining a hardness prediction value and a tensile strength prediction value based on JMatPro and the content of each component in the metal powder.

[0062] First, you need to call the Stainless Steel database and Mechanical Properties-Strength and Hardness calculation model in JMatPro, then enter the content of each component in the metal powder, and finally set the temperature for prediction. In order to ensure the accuracy of the prediction, the temperature can be set to the temperature actually used by the enterprise during sintering, such as 1200℃. Figure 3 The figure shows a case of hardness prediction value (Hardness) and tensile strength prediction value (Tensile Stress) output by JMatPro.

[0063] Step 202, determine whether the predicted hardness value is greater than or equal to the target hardness value and whether the predicted tensile strength value is greater than or equal to the target tensile strength value, if not, execute step 203, otherwise execute step 204.

[0064] Step 203, adding additional components according to a preset step length, and executing steps 201 to 202 for the metal powder after adding the additional components.

[0065] In one example, the preset step size may be set to 0.05 wt %.

[0066] In one example, the additional component is Ti and the existing components of the metal powder do not contain Ti. After the additional component is added, the content (i.e., mass percentage, in wt%) of each component in the metal powder will change and need to be recalculated. The calculation formula is as follows:

[0067]

[0068] in, is the mass percentage of each component in the metal powder after adding Ti, W 粉 is the mass of metal powder, W Ti is the mass of Ti, is the mass percentage of each component in the metal powder, W Ti The calculation formula is as follows:

[0069]

[0070] in, is the mass percentage of Ti.

[0071] Step 204, taking the current additional component content as the predicted lower limit value, and executing step 205.

[0072] Since the hardness and tensile strength will not be improved when the content of the additional component is too low, it is necessary to make multiple predictions at the preset step size to determine the lower limit of the preset range. When the content of the additional component is too high, it may cause abnormal growth of the crystal structure inside the metal, which will reduce the hardness and tensile strength, so it is also necessary to predict the upper limit of the preset range.

[0073] Step 205, continue to add additional ingredients according to the preset step length, and determine whether the current content of the additional ingredients is greater than the preset upper limit value. If it is greater, execute step 206, otherwise execute step 207.

[0074] In one example, considering the cost limitation, the preset upper limit value may be set to 2 wt %.

[0075] Step 206 , taking the difference between the current additional component content and the preset step length as the prediction upper limit value, and executing step 209 .

[0076] Step 207, for the metal powder after the additional components are added, first perform step 201 and then perform step 208;

[0077] Step 208, determining whether the predicted hardness value is greater than or equal to the target hardness value and whether the predicted tensile strength value is greater than or equal to the target tensile strength value, if yes, executing step 205, otherwise executing step 206;

[0078] Step 209: determine a preset range according to the prediction lower limit value and the prediction upper limit value.

[0079] Specifically, the process parameters include injection speed, injection pressure, holding time and sintering temperature, and the process parameters are within the process parameter range.

[0080] The process parameters are usually set based on the company's original experience. In one example, the process parameter range includes: injection speed range of 30-50mm / s, injection pressure range of 50-100MPa, holding time range of 1-10s, and sintering temperature range of 1200℃-1300℃.

[0081] Step 102, input prediction parameters based on the trained neural network to obtain a predicted value of shrinkage.

[0082] In one example, the neural network is a BP neural network, including an input layer, a hidden layer and an output layer. The BP neural network program can be written by MATLAB, and the structure is as follows: Figure 4 As shown, the neurons in the input layer receive the additional ingredient content of each product ( Figure 4Taking Ti element content as an example), hardness (the hardness test value is used during training, and the hardness target value is used during prediction), tensile strength (the tensile strength test value is used during training, and the tensile strength target value is used during prediction), injection speed, injection pressure, holding time and sintering temperature. The neurons in the output layer output the predicted value of shrinkage rate, and the neurons in the hidden layer receive the input of the neurons in the input layer. After information transmission between the neurons, the mapping relationship between the output and the input is obtained.

[0083] Specifically, the neural network is trained based on production data of different products.

[0084] In one example, the neural network is trained based on production data of different products including:

[0085] The production data of different products are organized into data sets and normalized;

[0086] The normalized data set is divided into training set and test set in a ratio of 8:2 to train the neural network.

[0087] The training function can use the Levenberg-Marquardt function, referred to as trainlm, which is mainly used for weight optimization and bias. Compared with other training functions such as traingd, trainrp, and traincgb, this function has the fastest convergence speed and can reduce the amount of calculation in training.

[0088] The training steps are as follows:

[0089] Initialize network weights and biases;

[0090] Calculate the network output and error under the initial weights and biases;

[0091] Calculate the gradient based on the error;

[0092] Use gradient information and residuals to build an approximate 2D model;

[0093] Calculate the Hessian matrix and update the weights based on the gradient;

[0094] Update weights and biases;

[0095] Check convergence until the error is less than the set threshold or the maximum number of iterations is reached, then stop training.

[0096] Specifically, different products are obtained through actual production tests based on metal powder, additional ingredients, preset ranges and process parameter ranges.

[0097] In one example, different products are obtained by:

[0098] Setting different production plans according to the preset range and process parameter range, the production plan includes the content of additional ingredients and process parameters;

[0099] Based on the metal powder and additional components, actual production tests are carried out according to the different production plans to obtain different products.

[0100] The actual production test includes: in the injection molding stage, the feed is put into the injection machine furnace, and after heating to the melting temperature of the feed, additional ingredients are added to the furnace according to the content of additional ingredients in the production plan, and then the injection molding, degreasing and sintering processes are completed according to the process parameters in the production plan to obtain a sintered blank.

[0101] Specifically, the production data includes the content of additional components, hardness test values, tensile strength test values, process parameters and shrinkage test values.

[0102] In one example, the hardness test value, tensile strength test value and shrinkage test value are obtained based on product testing. The hardness test value can be obtained by selecting six different test points on the sintered blank, measuring the hardness on a hardness tester and taking the average value. The hardness tester can be a Vickers hardness tester. Generally speaking, the more test points the better, and try to select different positions on different surfaces. The tensile strength test value must first be designed according to GB / T228.1-2021. The shape and size of the tensile specimen are then tested using a tensile testing machine and the tensile strength of the two tensile specimens is averaged. The tensile testing machine can be an electronic universal testing machine. The shrinkage test value is the ratio of the volume difference between the injection blank and the sintered blank to the volume of the injection blank.

[0103] Step 103, determining whether the predicted shrinkage rate value is greater than the target shrinkage rate value, if so, executing step 104, otherwise executing step 105.

[0104] For metal parts made by metal powder injection molding, the smaller the shrinkage, the better.

[0105] Step 104, adjusting the process parameters based on preset rules, and executing steps 101 to 103 for the adjusted process parameters.

[0106] In one example, the preset rule is determined in the following manner:

[0107] Select one process parameter from the prediction parameters as a variable in turn;

[0108] The corresponding prediction parameters when the variables are set to different values ​​are input into the neural network to obtain the predicted value of shrinkage rate;

[0109] The proportional relationship between the variable and the shrinkage rate is determined based on each value of the variable and its corresponding predicted shrinkage rate.

[0110] In one example, when Ti is used as an additional component, Figure 5 The shrinkage ratio (i.e. Figure 5 The predicted shrinkage rate in the figure is proportional to the injection speed, injection pressure, holding time and sintering temperature, where:

[0111] The injection speed is proportional to the shrinkage rate;

[0112] The injection pressure is proportional to the shrinkage rate;

[0113] The holding time is inversely proportional to the shrinkage rate;

[0114] The sintering temperature is inversely proportional to the shrinkage rate.

[0115] According to the preset rules when Ti is used as an additional component in the above example, if the predicted shrinkage value exceeds the target shrinkage value, the process parameters can be adjusted by reducing the injection speed, reducing the injection pressure, increasing the holding time, and increasing the sintering temperature.

[0116] Step 105, determining whether the process parameters meet the standards.

[0117] In the above scheme, based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and the preset upper limit value to determine the preset range of the additional component, a more accurate and reliable composition ratio of the metal powder can be obtained, thereby improving the rheological properties of the feed; at the same time, by optimizing the process parameters that match the composition ratio, not only the hardness and tensile strength of the metal accessories are improved, but also the shrinkage rate is reduced.

[0118] At present, all kinds of metal accessories manufactured by enterprises are basically made of similar materials. In one example, the content of each component in the metal powder is Cr: 17wt%, Ni: 1.5wt%, Mo: 2.5wt%, Si: 1wt%, Mn: 1wt%, C: 0.01wt% and Fe: 76.99wt%, and the additional component is Ti. The hardness target value is 28HRC, the tensile strength target value is 800MPa, and the shrinkage target value is 2%. The preset range is 0.3-1.0wt%. The predicted hardness value range based on the preset range is 28-29HRC, and the tensile strength range is 800-850MPa. The injection speed after neural network optimization is 42mm / s, the injection pressure is 80MPa, the holding time is 1s, the sintering temperature is 1280℃, and the predicted shrinkage value is 1.204%.

[0119] Based on the same inventive concept, Figure 6A schematic diagram of the structure of a device for optimizing process parameters of metal powder injection molding provided by an embodiment of the present invention is shown, comprising:

[0120] A setting module is used to set prediction parameters, which include the content of additional components, hardness target value, tensile strength target value and process parameters. The additional components are added to the metal powder to improve the hardness and tensile strength. The content of the additional components is within a preset range. The preset range is determined based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and the preset upper limit value. The process parameters include injection speed, injection pressure, holding time and sintering temperature. The process parameters are within the process parameter range.

[0121] A prediction module, which is used to input prediction parameters based on a trained neural network to obtain a predicted value of shrinkage, wherein the neural network is trained based on production data of different products, and the different products are obtained by actual production tests based on metal powder, additional ingredients, preset ranges and process parameter ranges, and the production data includes additional ingredient content, hardness test value, tensile strength test value, process parameters and shrinkage test value;

[0122] A judgment module, used to judge whether the predicted shrinkage rate value is greater than the target shrinkage rate value;

[0123] An adjustment module, used for adjusting the process parameters based on preset rules when the result of the judgment module is yes, and inputting the adjusted process parameters into the setting module;

[0124] The determination module is used to determine whether the process parameters meet the standards when the result of the determination module is negative.

[0125] Based on the same inventive concept, an embodiment of the present invention provides a computing device, including:

[0126] A memory for storing program instructions;

[0127] The processor is used to call the program instructions stored in the memory and execute the above method according to the obtained program.

[0128] Based on the same inventive concept, an embodiment of the present invention provides a computer-readable non-volatile storage medium, including computer-readable instructions. When a computer reads and executes the computer-readable instructions, the computer executes the above method.

[0129] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0130] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0131] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0132] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0133] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0134] Obviously, those skilled in the art can make various changes and modifications 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 claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for optimizing process parameters of metal powder injection molding, characterized in that: The following steps are involved: Step 101, setting prediction parameters, the prediction parameters include additional component content, hardness target value, tensile strength target value and process parameters, the additional component is used to be added to the metal powder to improve the hardness and tensile strength, the additional component content is within a preset range, the preset range is determined based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and a preset upper limit value, the process parameters include injection speed, injection pressure, holding time and sintering temperature, and the process parameters are within the process parameter range; Step 102: input the prediction parameters based on the trained neural network to obtain a predicted shrinkage value, wherein the neural network is trained based on production data of different products, and the different products are obtained by actual production tests based on the metal powder, the additional components, the preset range and the process parameter range, and the production data includes the additional component content, hardness test value, tensile strength test value, process parameters and shrinkage test value; Step 103, determining whether the predicted shrinkage rate value is greater than the target shrinkage rate value, if so, executing step 104, otherwise executing step 105; Step 104: adjusting the process parameters based on preset rules, and executing steps 101 to 103 for the adjusted process parameters; Step 105: Determine whether the process parameters meet the standards.

2. The method according to claim 1, characterized in that: The preset range is determined based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and the preset upper limit value, and includes the following steps: Step 201, obtaining a hardness prediction value and a tensile strength prediction value based on JMatPro and the content of each component in the metal powder; Step 202, judging whether the predicted hardness value is greater than or equal to the target hardness value and whether the predicted tensile strength value is greater than or equal to the target tensile strength value, if not, executing step 203, otherwise executing step 204; Step 203, adding the additional component according to a preset step length, and executing steps 201 to 202 for the metal powder after adding the additional component; Step 204, taking the current additional component content as the predicted lower limit value, and executing step 205; Step 205, continue to add the additional component according to the preset step length, and determine whether the current additional component content is greater than the preset upper limit value. If so, execute step 206, otherwise execute step 207; Step 206, taking the difference between the current additional component content and the preset step length as the prediction upper limit value, and executing step 209; Step 207, for the metal powder after the additional component is added, first perform step 201 and then perform step 208; Step 208, determining whether the predicted hardness value is greater than or equal to the target hardness value and whether the predicted tensile strength value is greater than or equal to the target tensile strength value, if yes, executing step 205, otherwise executing step 206; Step 209: Determine the preset range according to the prediction lower limit value and the prediction upper limit value.

3. The method according to claim 1, characterized in that: The neural network is a BP neural network, including an input layer, a hidden layer and an output layer.

4. The method according to claim 1, characterized in that: The neural network is trained based on production data of different products and includes: Arrange the production data of the different products into data sets and perform normalization processing; The normalized data set is divided into a training set and a test set in a ratio of 8:2 to train the neural network.

5. The method according to claim 1, characterized in that: The different products are obtained through actual production tests based on the metal powder, the additional components, the preset range and the process parameter range, including: Setting different production plans according to the preset range and the process parameter range, the production plans including the content of the additional component and the process parameters; The different products are obtained by carrying out actual production tests based on the metal powder and the additional components according to the different production plans.

6. The method according to claim 1, characterized in that: The hardness test value, the tensile strength test value and the shrinkage test value are obtained based on the product test.

7. The method according to claim 1, characterized in that: The preset rules are determined in the following way: Selecting one of the process parameters from the prediction parameters in turn as a variable; Inputting the prediction parameters corresponding to different values ​​of the variables into the neural network to obtain the predicted values ​​of the shrinkage rate; The proportional relationship between the variable and the shrinkage rate is determined based on each value of the variable and the corresponding predicted shrinkage rate value.

8. A device for optimizing process parameters of metal powder injection molding, characterized in that: include: A setting module, used to set prediction parameters, the prediction parameters include additional component content, hardness target value, tensile strength target value and process parameters, the additional component is used to be added to the metal powder to improve the hardness and tensile strength, the additional component content is within a preset range, the preset range is determined based on JMatPro, the content of each component in the metal powder, the hardness target value, the tensile strength target value and a preset upper limit value, the process parameters include injection speed, injection pressure, holding time and sintering temperature, and the process parameters are within the process parameter range; A prediction module, for inputting the prediction parameters based on a trained neural network to obtain a predicted value of shrinkage, wherein the neural network is trained based on production data of different products, and the different products are obtained by actual production tests based on the metal powder, the additional ingredients, the preset range and the process parameter range, wherein the production data includes the content of the additional ingredients, the hardness test value, the tensile strength test value, the process parameters and the shrinkage test value; A judgment module, used to judge whether the predicted shrinkage rate value is greater than the target shrinkage rate value; an adjustment module, configured to adjust the process parameters based on preset rules when the result of the judgment module is yes, and input the adjusted process parameters into the setting module; The determination module is used to determine that the process parameters meet the standards when the result of the determination module is no.

9. A computing device, characterized in that include: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory and execute the method according to any one of claims 1 to 7 according to the obtained program.

10. A computer-readable non-volatile storage medium, characterized in that: The method comprises computer-readable instructions, and when a computer reads and executes the computer-readable instructions, the computer executes the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Intelligent injection molding process parameter setting method based on scientific mold testing

    CN116461066A

  • Temperature measuring ring and method for calibrating temperature of injection molding titanium alloy sintering furnace

    CN117182077A

  • Method and computer system for predicting a shrinkage of a cast metal product

    EP3831511A1

Cited By

  • Mobile phone hinge injection molding parameter optimization method and system

    CN120632659A

  • A mobile phone hinge injection molding parameter optimization method and system

    CN120632659B