Aluminum alloy extrusion prediction optimization method based on machine learning and related device

Abstract

The invention provides an aluminum alloy extrusion prediction optimization method based on machine learning and a related device, and relates to the field of material plastic processing. According to the method, electronic equipment obtains a simulation model of the aluminum alloy extrusion process, and the simulation model can simulate the maximum extrusion stress and the outlet temperature of aluminum alloy through input simulation process parameters; generating a plurality of pieces of simulation data through the simulation model; and carrying out model training by utilizing the multiple pieces of simulation data to obtain a trained aluminum alloy extrusion model. In this way, a large amount of simulation data is generated through the finite element model and used for training the aluminum alloy extrusion model. According to the aluminum alloy extrusion model, the maximum extrusion stress and the outlet temperature of the aluminum alloy can be predicted according to the input design process parameters, so that a guidance basis is provided for actual extrusion production, and a production plan can be quickly adjusted.

Description

Technical Field

[0001] The present application relates to the field of material plastic processing, and more specifically, to an aluminum alloy extrusion prediction and optimization method based on machine learning and related devices. Background Art

[0002] Hot extrusion is mainly used to manufacture profiles, tubes, bars, various ultra-wide thin-walled profiles and small high-precision profiles. Due to the variety of extruded products, high precision and great production flexibility, hot extrusion production has become a key area of ​​industrial manufacturing. With the continuous development of manufacturing technology, hot extrusion products have been widely used in aerospace, transportation and other fields.

[0003] For aluminum extrusion technology, extrusion stress and outlet temperature are key factors that determine whether the product will have defects. Therefore, it is crucial to effectively predict the maximum extrusion stress and outlet temperature and determine the optimal parameters. The extrusion stress and outlet temperature of aluminum alloy extrusion are usually obtained through extrusion tests, but the extrusion test requires a lot of preparation work in the early stage and consumes a lot of time.

[0004] For example, before the extrusion test, the extruder needs to be preheated and the mold blank needs to be preheated and kept warm before the test can begin. During the test, the mold needs to be repaired and adjusted many times, which not only makes the entire test time-consuming, but also increases the workload. In addition, since the extrusion test consumes a large amount of aluminum, it will incur high material costs.

[0005] In view of this, the finite element analysis method is used in related technologies. Finite element analysis can systematically solve boundary value problems and can analyze parts with complex geometric shapes more accurately than experiments. Therefore, the use of finite element models can simulate multiple models at the same time without conducting experiments, without going through the preheating step in the test process, thereby significantly reducing the test time and cost, and providing an important engineering foundation for achieving efficient production of aluminum extrusion. This method is particularly important in order to predict the maximum extrusion stress and outlet temperature in aluminum alloy extrusion and reduce time costs.

[0006] However, in practice, it is found that large enterprises need to use more than 2,000 different molds every month, of which more than 50% are new molds. The cost of a single mold trial is between 1 million and 10 million yuan, and the annual mold trial cost is as high as about 40 billion yuan. Faced with such a huge demand for molds, traditional finite element analysis methods are unable to cope with the large amount of calculation and long calculation time. Even if finite element tools are used for simulation, it takes a lot of time. Summary of the invention

[0007] In order to overcome at least one of the shortcomings of the prior art, the present invention provides an aluminum alloy extrusion prediction optimization method based on machine learning and a related device, specifically comprising:

[0008] In a first aspect, the present application provides an aluminum alloy extrusion prediction optimization method based on machine learning, the method comprising:

[0009] Acquire a simulation model of an aluminum alloy extrusion process, wherein the simulation model can simulate the maximum extrusion stress and outlet temperature of the aluminum alloy using input simulation process parameters;

[0010] Generate multiple simulation data through the simulation model;

[0011] Model training is performed using a plurality of the simulation data to obtain a trained aluminum alloy extrusion model, wherein the aluminum alloy extrusion model is used to predict the maximum extrusion stress and outlet temperature of the aluminum alloy according to input design process parameters.

[0012] In combination with the optional implementation manner of the first aspect, the simulation model is a finite element model verified by measured data.

[0013] In combination with the optional implementation manner of the first aspect, a plurality of the simulation data are used to perform model training to obtain a trained aluminum alloy extrusion model, including:

[0014] Using the plurality of simulation data to train a plurality of models to be trained, to obtain a plurality of trained candidate models;

[0015] The model with the best prediction effect is selected from the multiple candidate models as the aluminum alloy extrusion model.

[0016] In combination with the optional implementation manner of the first aspect, each piece of simulation data includes a mold category and extrusion parameters;

[0017] Using the plurality of simulation data to train the plurality of models to be trained, a plurality of candidate models are obtained, including:

[0018] Preprocessing the process parameters of each piece of the simulation data to obtain preprocessed data of each piece of the simulation data, wherein the preprocessing method of the mold category is thermal coding, and the preprocessing method of the extrusion parameter is standardization processing;

[0019] The plurality of pre-processed data are input into the plurality of models to be trained for training, so as to obtain a plurality of trained candidate models.

[0020] In combination with the optional implementation manner of the first aspect, the extrusion parameters include extrusion speed, extrusion temperature, extrusion barrel temperature, and friction coefficient.

[0021] In combination with an optional implementation manner of the first aspect, the friction coefficient in the extrusion parameter is obtained by mapping the extrusion temperature in the extrusion parameter.

[0022] In combination with the optional implementation manner of the first aspect, the relationship between the friction coefficient in the extrusion parameter and the extrusion barrel temperature is:

[0023]

[0024] Wherein, μ(T) represents the friction coefficient when the extrusion barrel temperature is T, T0 represents room temperature, μ(T0) represents the friction coefficient at room temperature, and a, b, and n represent preset coefficients, respectively.

[0025] In a second aspect, the present application also provides an aluminum alloy extrusion prediction and optimization device based on machine learning, the method comprising:

[0026] A data generation module, used to obtain a simulation model of an aluminum alloy extrusion process, wherein the simulation model can simulate the maximum extrusion stress and outlet temperature of the aluminum alloy using input simulation process parameters;

[0027] The data generation module is further used to generate multiple simulation data through the simulation model;

[0028] The model training module is used to perform model training using multiple simulation data to obtain a trained aluminum alloy extrusion model, wherein the aluminum alloy extrusion model is used to predict the maximum extrusion stress and outlet temperature of the aluminum alloy according to the input design process parameters.

[0029] In combination with the optional implementation manner of the second aspect, the simulation model is a finite element model verified by measured data.

[0030] In conjunction with the optional implementation manner of the second aspect, the model training module is further specifically used for:

[0031] Using the plurality of simulation data to train a plurality of models to be trained, to obtain a plurality of trained candidate models;

[0032] The model with the best prediction effect is selected from the multiple candidate models as the aluminum alloy extrusion model.

[0033] In conjunction with the optional implementation manner of the second aspect, each piece of simulation data includes a mold category and an extrusion parameter; and the model training module is further specifically used for:

[0034] Preprocessing the process parameters of each piece of the simulation data to obtain preprocessed data of each piece of the simulation data, wherein the preprocessing method of the mold category is thermal coding, and the preprocessing method of the extrusion parameter is standardization processing;

[0035] The plurality of pre-processed data are input into the plurality of models to be trained for training, so as to obtain a plurality of trained candidate models.

[0036] In combination with the optional implementation manner of the second aspect, the extrusion parameters include extrusion speed, extrusion temperature, extrusion barrel temperature, and friction coefficient.

[0037] In combination with an optional implementation manner of the second aspect, the friction coefficient in the extrusion parameter is obtained by mapping the extrusion temperature in the extrusion parameter.

[0038] In conjunction with the optional implementation manner of the second aspect, the relationship between the friction coefficient in the extrusion parameter and the extrusion barrel temperature is:

[0039]

[0040] Wherein, μ(T) represents the friction coefficient when the extrusion barrel temperature is T, T0 represents room temperature, μ(T0) represents the friction coefficient at room temperature, and a, b, and n represent preset coefficients, respectively.

[0041] In a third aspect, the present application also provides a storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the aluminum alloy extrusion prediction and optimization method based on machine learning.

[0042] In a fourth aspect, the present application also provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the aluminum alloy extrusion prediction and optimization method based on machine learning is implemented.

[0043] Compared with the prior art, this application has the following beneficial effects:

[0044] The present application provides an aluminum alloy extrusion prediction optimization method based on machine learning and a related device. In the method, an electronic device obtains a simulation model of an aluminum alloy extrusion process, wherein the simulation model can simulate the maximum extrusion stress and outlet temperature of the aluminum alloy using input simulation process parameters; a plurality of simulation data are generated by the simulation model; and a model is trained using the plurality of simulation data to obtain a trained aluminum alloy extrusion model. In this way, a large amount of simulation data is generated using a finite element model and used to train an aluminum alloy extrusion model. The aluminum alloy extrusion model can predict the maximum extrusion stress and outlet temperature of the aluminum alloy based on the input design process parameters, thereby providing a guiding basis for actual extrusion production and facilitating rapid adjustment of production plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A schematic diagram of a process flow of an aluminum alloy extrusion prediction and optimization method based on machine learning provided in an embodiment of the present application;

[0047] Figure 2 A test comparison chart of extrusion stress provided in the embodiments of the present application;

[0048] Figure 3 A test comparison chart of the outlet temperature provided in the embodiment of the present application;

[0049] Figure 4 A schematic diagram of the structure of the aluminum alloy extrusion prediction and optimization method based on machine learning provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0052] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0053] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0054] In the description of the present application, it should be noted that the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. In addition, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0055] Based on the above statement, as introduced in the background technology, although the finite element model can simulate multiple models at the same time without testing, and there is no need to go through the preheating step in the test process, thereby significantly reducing the test time and cost. However, in the face of the huge mold demand of large enterprises, the traditional finite element analysis method is unable to cope with the large amount of calculation and long calculation time. Even if the finite element tool is used for simulation, it takes a lot of time.

[0056] Based on the discovery of the above technical problems, the inventors have proposed the following technical solutions to solve or improve the above problems through creative work. It should be noted that the defects in the solutions in the above prior art are the results obtained by the inventors after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the embodiments of the present application for the above problems below should all be the contributions made by the inventors to the present application in the process of invention and creation, and should not be understood as technical contents known to those skilled in the art.

[0057] In view of the above problems, this embodiment provides an aluminum alloy extrusion prediction optimization method based on machine learning. In this method, an electronic device obtains a simulation model of an aluminum alloy extrusion process, wherein the simulation model can simulate the maximum extrusion stress and outlet temperature of the aluminum alloy using the input simulation process parameters; a plurality of simulation data are generated by the simulation model; and a model is trained using the plurality of simulation data to obtain a trained aluminum alloy extrusion model. In this way, a large amount of simulation data is generated using a finite element model and used to train an aluminum alloy extrusion model. The aluminum alloy extrusion model can predict the maximum extrusion stress and outlet temperature of the aluminum alloy based on the input design process parameters, thereby providing a guiding basis for actual extrusion production and facilitating rapid adjustment of production plans.

[0058] It should be noted that the electronic device for implementing the above-mentioned machine learning-based aluminum alloy extrusion prediction and optimization method may be, but is not limited to, a mobile terminal, a tablet computer, a laptop computer, a desktop computer, a server, etc., as long as sufficient computing power support can be provided. The server may be a single server or a server group. The server group may be centralized or distributed (for example, the server may be a distributed system). In some embodiments, the server may be local or remote relative to the user terminal. In some embodiments, the server may be implemented on a cloud platform; as an example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (Community Cloud), a distributed cloud, an inter-cloud (Inter-Cloud), a multi-cloud (Multi-Cloud), etc., or any combination thereof. In some embodiments, the server may be implemented on an electronic device having one or more components.

[0059] To make the solution provided by this embodiment clearer, the following uses a server as an electronic device to implement the method, and combines Figure 1 Each step of the method is described in detail. However, it should be understood that the operations of the flowchart may not be implemented in order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowchart, or remove one or more operations from the flowchart under the guidance of the content of this application. Figure 1 As shown, the method includes:

[0060] S1, obtain the simulation model of aluminum alloy extrusion process.

[0061] The simulation model can simulate the maximum extrusion stress and outlet temperature of the aluminum alloy using the input simulation process parameters. In this embodiment, the simulation model can be a finite element model verified by actual measured data.

[0062] In order to verify the constructed finite element model, as an optional implementation, an actual aluminum alloy extrusion test can be carried out to collect data such as the maximum extrusion stress and outlet temperature during the extrusion process, which are used to verify the accuracy of subsequent simulations. Then, the size of the billet is set according to actual requirements, and a three-dimensional geometric model of the extrusion cylinder, billet and extrusion rod is established. Then, the established three-dimensional geometric model is input into the finite element simulation software (such as Deform-3D), and the process parameters, material parameters and simulation control parameters of the material are set according to the actual experimental requirements, including extrusion speed, extrusion temperature, mold temperature, friction coefficient, thermal conductivity, mesh refinement size, etc. The simulation is run through the finite element simulation software to generate simulation data, and the simulation data is compared and verified with the test results. If there is a deviation between the two, the finite element model is continued to be adjusted until the results of the two are within the error range, so as to ensure the accuracy of the model.

[0063] In this embodiment, a finite element model is constructed using 7N01 aluminum alloy as the research object, wherein the material parameters of 7N01 are shown in the following table:

[0064] element Si Fe Cu Mn Mg Cr Zn Ti Al Content / w% <0.030 <0.35 0.20 0.15 1.80 0.20 5.0 0.10 Bal.

[0065] In addition, the material performance parameters of 7N01 are shown in the following table:

[0066]

[0067] Of course, the method provided in this embodiment is not limited to 7N01 aluminum alloy, but is also applicable to other types of aluminum alloys.

[0068] Combined with the above implementation of the simulation model in step S1, continue to refer to Figure 1 , the method further comprises:

[0069] S2, generating multiple simulation data through the simulation model.

[0070] It should be noted that the final prediction effect of the neural network model is directly related to the quality and quantity of the training samples. During the research process, it was found that there is very little data related to the hot extrusion forming process of aluminum alloy. Therefore, in order to obtain a sufficient number of training samples, this embodiment generates a large number of them through a simulation model.

[0071] Exemplarily, continuing to take the above finite element model as an example, the server can receive different parameters set by the user according to the actual experimental requirements, simulate and record the extrusion stress and outlet temperature generated, and form multiple simulation data to constitute a data set for subsequent machine learning training. As an optional implementation, each simulation data includes a mold category and extrusion parameters. Among them, the mold category in each simulation data is one of profiles, bars, pipes, and plates. Extrusion parameters include extrusion speed, extrusion temperature, mold temperature, extrusion barrel temperature, friction coefficient and other parameters.

[0072] It is worth mentioning that during the research process, it was found that compared with other parameters in the extrusion parameters that can be set arbitrarily by the user, the friction coefficient is not a constant related to the material, but a parameter that changes with temperature. It was further found during the research process that the friction coefficient is affected by the temperature of the extrusion barrel. Therefore, the friction coefficient in the extrusion parameters is obtained by mapping the extrusion barrel temperature in the extrusion parameters. In order to obtain the mapping relationship between the two, after fitting with a large amount of measured data in this embodiment, the relationship between the friction coefficient in the extrusion parameters and the extrusion barrel temperature is obtained as follows:

[0073]

[0074] In the formula, μ(T) represents the friction coefficient when the extrusion barrel temperature is T, T0 represents room temperature, μ(T0) represents the friction coefficient at room temperature, a, b, and n represent preset coefficients, respectively, and these coefficients are obtained through fitting.

[0075] Combined with the above implementation, the introduction of multiple simulation data in step S2 is continued. Figure 1 , the method further comprises:

[0076] S3, using multiple simulation data to perform model training to obtain a trained aluminum alloy extrusion model.

[0077] The aluminum alloy extrusion model is used to predict the maximum extrusion stress and outlet temperature of the aluminum alloy according to the input design process parameters. Given that there are currently a large number of machine learning models available, not every model is suitable for the application scenario of this embodiment. In this regard, this embodiment provides the following optional implementation of step S3:

[0078] S3-1, using multiple simulation data to train multiple models to be trained, to obtain multiple trained candidate models.

[0079] During the research, we learned that Scikit-learn is an open source machine learning library. It is built on open source projects such as NumPy, SciPy, and matplotlib, and provides a series of simple and effective tools for data mining and data analysis. Therefore, Scikit-learn has a wide range of machine learning and data mining functions, including but not limited to classification, regression, clustering, data preprocessing, model selection and evaluation, etc.

[0080] Therefore, the above-mentioned multiple models to be trained can include 9 machine learning models in Scikit-learn, including K-Nearest Neighbors (K nearest neighbor algorithm), RIDGE regression, LASSO regression, Decision Tree, Random Forest, eXtreme Gradient Boosting, LinearSupport Vector Machine (support vector machine regression-linear kernel function), Support Vector Machine_RBF (support vector machine regression-Gaussian kernel function) and Adaptive boosting.

[0081] Based on the above-mentioned introduction to multiple models to be trained, as an optional implementation method, the server can preprocess the process parameters of each simulation data to obtain preprocessed data for each simulation data, wherein the preprocessing method of the mold category is thermal unique encoding, and the preprocessing method of the extrusion parameter is standardized processing; the multiple preprocessed data are input into multiple models to be trained for training to obtain multiple trained candidate models.

[0082] For the above implementation, it should be understood that the mold categories such as profiles, bars, tubes, and plates are not continuous numerical features and cannot be directly involved in the machine learning model training. This implementation performs one-hot encoding on them. In a specific implementation, the server can use the OneHotEncoder function in sklearn.preprocessing to perform one-hot encoding on them, encode profiles as 1000, plates as 0100, tubes as 0010, and bars as 0001, and add them to the feature combination.

[0083] In addition, it should be understood that in the machine learning algorithm, there should be no high correlation between features. If the magnitudes of the features are very different, the algorithm will be difficult to converge or require a long training time. Therefore, in this embodiment, the Z-Score standardization method can be used to pre-process the extrusion parameters to obtain standardized data.

[0084] Among them, Z-Score standardization, also known as standardization or standard score standardization, performs feature scaling by adjusting the mean and standard deviation of the feature so that the mean of each feature is 0 and the standard deviation is 1. For each parameter in the squeeze parameter, the formula used by Z-Score standardization is as follows:

[0085]

[0086] In the formula, x z-score represents the extrusion parameter after standardization by standard deviation, x represents the original extrusion parameter, μ represents the mean of characteristic data, and σ represents the standard deviation of the extrusion parameter.

[0087] In this way, a plurality of pre-processed data are obtained by using the above implementation mode, and are respectively input into different models to be trained for training, thereby obtaining a plurality of candidate models.

[0088] S3-2, selecting the model with the best prediction effect from multiple candidate models as the aluminum alloy extrusion model.

[0089] In this regard, we continue to use the above 9 models as examples and refer to them as KNN, RIDGE, LASSO, DT, RF, XGBOOST, SVM LINEAR, SVM RBF and ADA. 2 As an evaluation index of generalization performance, R 2 The closer the value is to 1, the better the fit. The above 9 models were tested using the test set, and the test results are as follows: Figure 2 , Figure 3 As shown. Among them, Figure 2 The squeeze stress R of each model tested on 10 training runs is shown. 2 Comparison chart of mean results, Figure 3 The outlet temperature R of the test set of each model trained 10 times is shown 2 The mean results are compared in Figure 2. After comparison, it is not difficult to see that the RF random forest model has a higher R 2 The values ​​are 0.88 and 0.9 respectively, so this model performs the best among the 9 models.

[0090] Finally, this embodiment also uses the trained aluminum alloy extrusion model to predict random parameters, conducts experiments on the prediction results, and compares and analyzes the errors and optimization effect evaluation between the prediction results of the aluminum alloy extrusion model and the test data. Some parameters in the test process are shown in the following table:

[0091] Extrusion temperature℃ Mold temperature Extrusion barrel temperature Extrusion speed 490 480 440 1.5

[0092] During the test, the billet will deform sharply after extrusion and generate a lot of heat, causing the outlet temperature to rise sharply. As the extrusion enters a steady state, the outlet temperature of the billet gradually stabilizes. The test results show that the average outlet temperature is about 513.5 degrees. Under the same parameters, the aluminum alloy extrusion model predicts the outlet temperature to be 507.5 degrees, with an error of 1.1%, thus meeting the requirements.

[0093] Based on the same inventive concept as the aluminum alloy extrusion prediction optimization method based on machine learning provided in this embodiment, this embodiment also provides an aluminum alloy extrusion prediction optimization device based on machine learning, which includes at least one software function module that can be stored in a memory or solidified in an electronic device in the form of software. The processor in the electronic device is used to execute the executable module stored in the memory. For example, the software function module and computer program included in the device. Please refer to Figure 4 , functionally speaking, the device may include:

[0094] A data generation module 11 is used to obtain a simulation model of an aluminum alloy extrusion process, wherein the simulation model can simulate the maximum extrusion stress and outlet temperature of the aluminum alloy using input simulation process parameters;

[0095] The data generation module 11 is also used to generate multiple simulation data through the simulation model;

[0096] The model training module 12 is used to perform model training using multiple simulation data to obtain a trained aluminum alloy extrusion model, wherein the aluminum alloy extrusion model is used to predict the maximum extrusion stress and outlet temperature of the aluminum alloy based on the input design process parameters.

[0097] In this embodiment, the data generation module 11 is used to implement Figure 1 In steps S1 and S2, the model training module 12 is used to implement Figure 1 Therefore, for the detailed description of each of the above modules, please refer to the specific implementation of the corresponding step. Of course, since the invention concept is the same as that of the aluminum alloy extrusion prediction and optimization method based on machine learning, the aluminum alloy extrusion prediction and optimization device based on machine learning can also implement other steps or sub-steps of the method through the above modules, which will not be described in detail in this implementation.

[0098] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0099] It should also be understood that if the above implementation is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0100] Therefore, this embodiment further provides a storage medium, which is a computer-readable storage medium. The storage medium stores a computer program, and when the computer program is executed by a processor, the aluminum alloy extrusion prediction optimization method based on machine learning provided in this embodiment is implemented. Among them, the storage medium can be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc., which can store program codes.

[0101] This embodiment provides an electronic device for implementing an aluminum alloy extrusion prediction optimization method based on machine learning. Figure 5 As shown, the electronic device may include a processor 22 and a memory 21. In addition, the memory 21 stores a computer program, and the processor implements the aluminum alloy extrusion prediction and optimization method based on machine learning provided in this embodiment by reading and executing the computer program corresponding to the above implementation in the memory 21.

[0102] Continue to see Figure 5 The electronic device may further include a communication unit 23. The memory 21, the processor 22 and the communication unit 23 are electrically connected to each other directly or indirectly through a system bus 24 to achieve data transmission or interaction.

[0103] The memory 21 may be an information recording device based on any electronic, magnetic, optical or other physical principle, used to record execution instructions, data, etc. In some embodiments, the memory 21 may be, but is not limited to, a volatile memory, a non-volatile memory, a storage drive, etc.

[0104] In some embodiments, the volatile memory may be a random access memory (RAM); in some embodiments, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), a flash memory, etc.; in some embodiments, the storage drive may be a disk drive, a solid-state drive, any type of storage disk (such as a CD, a DVD, etc.), or a similar storage medium, or a combination thereof, etc.

[0105] The communication unit 23 is used to send and receive data through a network. In some embodiments, the network may include a wired network, a wireless network, a fiber optic network, a telecommunication network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include a wired or wireless network access point, such as a base station and / or a network switching node, through which one or more components of the service request processing system may be connected to the network to exchange data and / or information.

[0106] The processor 22 may be an integrated circuit chip having a signal processing capability, and the processor may include one or more processing cores (e.g., a single-core processor or a multi-core processor). By way of example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), or a microprocessor, or any combination thereof.

[0107] Understandably, Figure 5 The structure shown is for illustration only. The electronic device 100 may also have Figure 5 More or fewer components than shown, or with Figure 5 Different configurations are shown. Figure 5 The components shown may be implemented in hardware, software or a combination thereof.

[0108] It should be understood that the apparatus and method disclosed in the above-mentioned embodiments can also be implemented in other ways. The apparatus embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the apparatus, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0109] The above are only various implementations of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A machine learning-based aluminum alloy extrusion prediction and optimization method, characterized in that: The method comprises: Acquire a simulation model of an aluminum alloy extrusion process, wherein the simulation model can simulate the maximum extrusion stress and outlet temperature of the aluminum alloy using input simulation process parameters; Generate multiple simulation data through the simulation model; Model training is performed using a plurality of the simulation data to obtain a trained aluminum alloy extrusion model, wherein the aluminum alloy extrusion model is used to predict the maximum extrusion stress and outlet temperature of the aluminum alloy according to input design process parameters.

2. The aluminum alloy extrusion prediction and optimization method based on machine learning according to claim 1 is characterized in that: The simulation model is a finite element model verified by measured data.

3. The aluminum alloy extrusion prediction and optimization method based on machine learning according to claim 1 is characterized in that: The model is trained by using a plurality of the simulation data to obtain a trained aluminum alloy extrusion model, including: Using the plurality of simulation data to train a plurality of models to be trained, to obtain a plurality of trained candidate models; The model with the best prediction effect is selected from the multiple candidate models as the aluminum alloy extrusion model.

4. The aluminum alloy extrusion prediction and optimization method based on machine learning according to claim 3 is characterized in that: Each piece of simulation data includes a die type and extrusion parameters; Using the plurality of simulation data to train the plurality of models to be trained, a plurality of candidate models are obtained, including: Preprocessing the process parameters of each piece of the simulation data to obtain preprocessed data of each piece of the simulation data, wherein the preprocessing method of the mold category is thermal coding, and the preprocessing method of the extrusion parameter is standardization processing; The plurality of pre-processed data are input into the plurality of models to be trained for training, so as to obtain a plurality of trained candidate models.

5. The aluminum alloy extrusion prediction and optimization method based on machine learning according to claim 4 is characterized in that: The extrusion parameters include extrusion speed, extrusion temperature, extrusion barrel temperature, and friction coefficient.

6. The aluminum alloy extrusion prediction and optimization method based on machine learning according to claim 5 is characterized in that: The friction coefficient in the extrusion parameters is obtained by mapping the extrusion temperature in the extrusion parameters.

7. The aluminum alloy extrusion prediction and optimization method based on machine learning according to claim 6 is characterized in that: The relationship between the friction coefficient in the extrusion parameters and the extrusion barrel temperature is: Wherein, μ(T) represents the friction coefficient when the extrusion barrel temperature is T, T0 represents room temperature, μ(T0) represents the friction coefficient at room temperature, and a, b, and n represent preset coefficients, respectively.

8. A machine learning-based aluminum alloy extrusion prediction and optimization device, characterized in that: The device comprises: A data generation module, used to obtain a simulation model of an aluminum alloy extrusion process, wherein the simulation model can simulate the maximum extrusion stress and outlet temperature of the aluminum alloy using input simulation process parameters; The data generation module is further used to generate multiple simulation data through the simulation model; The model training module is used to perform model training using multiple simulation data to obtain a trained aluminum alloy extrusion model, wherein the aluminum alloy extrusion model is used to predict the maximum extrusion stress and outlet temperature of the aluminum alloy according to the input design process parameters.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting and optimizing aluminum alloy extrusion based on machine learning described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory, the memory stores a computer program, and when the computer program is executed by the processor, the machine learning-based aluminum alloy extrusion prediction and optimization method described in any one of claims 1 to 7 is implemented.

Images