Dot matrix structure mechanical property simulation method, device and system for additive manufacturing

Abstract

The invention relates to a dot matrix structure mechanical property simulation method, device and system for additive manufacturing. The method comprises the steps that pixel point measurement is conducted according to a three-dimensional object image, and a forming rod diameter is generated; using a machine learning method to train and fit an inclination angle-rod diameter, predicting a forming rod diameter according to a design value, and using a predicted value to establish a lattice structure model; a compression test is conducted, a machine learning method is used for training and fitting diameter-mechanical parameters, a mechanical test model is established, and the elastic modulus of the average forming diameter is predicted; and establishing a finite element simulation model, inputting the predicted elastic modulus value into the finite element simulation model for mechanical property analysis, and adjusting and fitting the finite element simulation model according to a generated mechanical property analysis result. The forming size deviation of a three-dimensional object and the forming quality of a currently used process can be measured through an experiment, and then the macroscopic mechanical deviation caused by the size effect of a microstructure is compensated through finite element software, so that mechanical property simulation is realized.

Description

Technical Field

[0001] The present application relates to the technical field of finite element numerical simulation, and more specifically to a method, device, system and electronic equipment for simulating mechanical properties of a lattice structure for additive manufacturing. Background Art

[0002] In laser additive manufacturing, because the spot diameter and scanning layer thickness do not approach zero, as the laser spot moves on the powder bed, the surface of the part exists in the form of overlapping melt paths, resulting in peaks and valleys between the melt paths that are convex in the middle and concave on both sides, forming a step effect.

[0003] Since the rod diameter of the lattice structure is usually small (millimeter level) and the units are densely arranged, it is greatly affected by the forming accuracy of the printing equipment during the preparation process. This influence causes the melt path to have a significant impact on the dimensional deviation, and the final formed sample shows an obvious step effect. It is precisely because of this step effect that there is a large difference between the simulation calculation results and the mechanical experimental results. Summary of the invention

[0004] The present application provides a method, device and system for simulating the mechanical properties of lattice structures for additive manufacturing, which can experimentally measure the forming size deviation of three-dimensional objects and the forming quality of the current process, and then compensate for the macroscopic mechanical deviation caused by the size effect of the microstructure through secondary development of finite element software to achieve mechanical property simulation.

[0005] In a first aspect, the present application provides a method for simulating the mechanical properties of a lattice structure for additive manufacturing, comprising: performing pixel measurement based on a formed three-dimensional object image containing a variety of diameters and pillar inclination angles to generate a formed rod diameter; taking the rod diameter and inclination angle as input, taking the formed rod diameter as output, and training using a machine learning artificial neural network method to fit the inclination angle-rod diameter, and then predicting the formed rod diameter based on the design value, and using the predicted value to establish a lattice structure model; performing compression tests on three-dimensional compression mechanical specimens of different diameters, obtaining mechanical parameters of different diameters, and training and fitting diameter-mechanical parameters using a machine learning artificial neural network method to establish a mechanical test model, and then predicting the elastic modulus of the average formed diameter; establishing a finite element simulation model based on the lattice structure model and the mechanical test model, and inputting the predicted elastic modulus value into the finite element simulation model as a material parameter, performing mechanical property analysis, and then adjusting and fitting the finite element simulation model based on the generated mechanical property analysis results.

[0006] In an optional scheme of the first aspect, when generating the diameter of the formed rod, the method includes: using additive manufacturing technology to form a three-dimensional object including a variety of diameters and pillar inclination angles; using an optical microscope device to photograph the three-dimensional object to generate a three-dimensional object image including a variety of diameters and pillar inclination angles; binarizing the three-dimensional object image and obtaining the pixel diameter of the formed rod; converting the pixel diameter into an actual diameter according to the pixel resolution of the optical microscope device to generate the diameter of the formed rod.

[0007] In an optional scheme of the first aspect, when using a machine learning artificial neural network method for training, the method includes: importing a module set for implementing data processing, modeling and evaluation; loading data containing rod diameter and inclination angle characteristics and normalizing the data to generate a first data set containing a training set and a test set; using a multilayer perceptron to construct a neural network regression model to fit the inclination angle-rod diameter and set the neural network parameters and the number of iterations, and then using the training set to train the neural network regression model; using the test set to predict the trained neural network regression model and calculate the mean square error and determination coefficient to evaluate the model; predicting the formed rod diameter through the neural network regression model according to the design value, and then using the predicted value to establish a lattice structure model.

[0008] In an optional scheme of the first aspect, when obtaining mechanical parameters of different diameters, the method includes: using additive manufacturing technology to form three-dimensional compressive mechanical specimens of different diameters; using material testing equipment to perform mechanical compression tests on three-dimensional compressive mechanical specimens of different diameters and record experimental results including compression load and displacement values; calculating the elastic modulus based on the experimental results and generating mechanical data based on the diameter of each three-dimensional compressive mechanical specimen and the matching elastic modulus.

[0009] In an optional scheme of the first aspect, when using a machine learning artificial neural network method for training, the method includes: importing a module set for implementing data processing, modeling and evaluation; loading data containing diameter and elastic modulus characteristics and normalizing the data to generate a second data set containing a training set and a test set; using a multilayer perceptron to construct a neural network regression model to fit diameter-mechanical parameters and set neural network parameters and the number of iterations, and then using the training set to train the neural network regression model; using the test set to predict the trained neural network regression model and calculate the mean square error and determination coefficient to perform model evaluation; setting the neural network regression model that meets preset requirements as a mechanical test model, and then predicting the elastic modulus of the average forming diameter based on the mechanical test model.

[0010] In an optional scheme of the first aspect, when importing a program library that implements data processing, modeling and evaluation, the method includes: importing a set of modules that provide reading and processing data; importing a set of modules that provide machine learning algorithms and tools; importing a set of modules for numerical operations.

[0011] In an optional scheme of the first aspect, when the neural network regression model is trained using a training set, the method includes: using the average error as the loss function of the neural network regression model; setting the hidden layer and the number of neurons it contains and setting the maximum number of training iterations; and using back propagation and gradient descent methods to optimize model parameters.

[0012] In an optional solution of the first aspect, when establishing the finite element simulation model, the method includes:

[0013] Set material properties; set dynamic analysis parameters, including analysis step, mass scaling, target time increment, field output and history output type; mesh the lattice structure model and assemble the mechanical test model to form a finite element simulation model; define external loads and boundary conditions to which the structure is subjected in the dynamic analysis.

[0014] In an optional solution of the first aspect, when setting the material properties, the method includes: setting the basic properties of the material, including material density, elastic modulus and Poisson's ratio; setting the plastic properties of the material, including stress and strain;

[0015] Set rate-dependent properties of materials; set material damage properties, including damage parameters and damage evolution.

[0016] In an optional scheme of the first aspect, when the finite element simulation model is adjusted and fitted according to the generated mechanical property analysis results, the method includes: comparing the generated mechanical property analysis results with the actual experimental data to generate error results; performing error analysis based on the error results and defining an error function based on the difference between the quantified experimental value and the simulation value; adjusting the parameters of the finite element simulation model according to the error function; and iterating and optimizing the finite element simulation model to minimize the error function.

[0017] In the second aspect, the present application provides a lattice structure mechanical property simulation device for additive manufacturing using the above-mentioned simulation method, including: an image processing module, which is used to measure pixel points according to the formed three-dimensional object image containing multiple diameters and pillar inclination angles, and generate a formed rod diameter; a first training module, which is used to take the rod diameter and inclination angle as input, the formed rod diameter as output, and use a machine learning artificial neural network method for training, fit the inclination angle-rod diameter, and then predict the formed rod diameter according to the design value, and use the predicted value to establish a lattice structure model; a second training module, which is used to perform compression tests on three-dimensional compression mechanical specimens of different diameters, obtain mechanical parameters of different diameters, and use a machine learning artificial neural network method for training and fitting diameter-mechanical parameters, establish a mechanical test model, and then predict the elastic modulus of the average formed diameter; a finite element simulation module, which is used to establish a finite element simulation model according to the lattice structure model and the mechanical test model, and input the predicted elastic modulus value as a material parameter into the finite element simulation model, perform mechanical property analysis, and then adjust and fit the finite element simulation model according to the generated mechanical property analysis results.

[0018] In the third aspect, the present application provides a lattice structure mechanical properties simulation system for additive manufacturing, which includes the above-mentioned simulation device, and also includes: additive manufacturing equipment for forming three-dimensional objects and three-dimensional compression mechanical specimens using additive manufacturing technology; optical microscope equipment for taking images; material testing equipment for conducting material mechanics experiments.

[0019] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate one or more embodiments of the present application and, together with the description, serve to explain the principles of the present application and to enable one of ordinary skill in the relevant art to make and use the present application.

[0021] Figure 1 It is a structural schematic diagram based on the existing actual objects of rods with different inclination angles and partial enlargement.

[0022] Figure 2 It is a flowchart of an exemplary method for simulating mechanical properties of lattice structures for additive manufacturing according to some embodiments of the present application.

[0023] Figure 3 This is a schematic diagram of an exemplary sample including various diameters and pillar inclination angles according to some embodiments of the present application.

[0024] Figure 4It is a schematic diagram of completing the conversion of a design model into a finite element simulation model based on a predicted value of a forming rod diameter according to some embodiments of the present application.

[0025] Figure 5 It is a schematic diagram of the compression process of an exemplary three-dimensional compression mechanical specimen according to some embodiments of the present application.

[0026] Figure 6 It is a schematic diagram of an exemplary mechanical simulation result according to some embodiments of the present application.

[0027] Figure 7 It is a schematic diagram of an exemplary mechanical experimental result according to some embodiments of the present application.

[0028] Figure 8 It is a schematic diagram of an exemplary mechanical experiment and simulation comparison according to some embodiments of the present application.

[0029] Fig. 9 It is a schematic diagram of a kinetic energy-internal energy curve of an exemplary simulation process according to some embodiments of the present application.

[0030] Fig.10 It is a schematic diagram comparing an exemplary simulation method of the present application and experimental results according to some embodiments of the present application.

[0031] Fig.11 It is a schematic diagram comparing an exemplary simulation method of the present application and an uncorrected simulation according to some embodiments of the present application.

[0032] Fig.12 It is a comparative schematic diagram of an exemplary simulation method of the present application, experimental results and uncorrected simulation according to some embodiments of the present application.

[0033] Fig.13 It is a connection diagram of an exemplary lattice structure mechanical property simulation system for additive manufacturing according to some embodiments of the present application.

[0034] Fig.14 It is a schematic diagram of the structure of an exemplary electronic device according to some embodiments of the present application. DETAILED DESCRIPTION

[0035] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present application will be more comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application.

[0036] Additive manufacturing technology is an integrated manufacturing technology that builds three-dimensional objects by stacking materials layer by layer. This technology uses heat sources such as lasers to melt powder or wire, increase the density of parts, and improve material utilization.

[0037] The lattice structure is a topologically ordered three-dimensional structure composed of multiple repeated unit cells arranged periodically in space. This structure has excellent specific strength, specific stiffness, energy absorption and shock absorption properties. It has been theoretically proven to be an effective structure that greatly reduces the relative density of components while ensuring reliable mechanical properties.

[0038] Finite element numerical simulation refers to the approximate solution of differential equations by discretizing continuous objects or systems into a finite number of units. It is used to predict and analyze the behavior of complex physical systems in fields such as structural mechanics, heat conduction, fluid dynamics, and electromagnetism. The advantage of finite element numerical simulation is that it can handle complex geometric shapes and boundary conditions as well as nonlinear material behavior. At present, there are many mature finite element software for academic research and engineering applications, such as ABAQUS; in the simulation method of lattice structure, finite element numerical simulation can be used to evaluate the mechanical properties of different lattice structures, such as elastic modulus and compressive strength. Through the secondary development of ABAQUS, a large number of different structures can be efficiently evaluated, greatly improving efficiency and accuracy.

[0039] In order to ensure the accuracy of simulation calculations during the manufacturing process of the lattice structure, a three-dimensional model that fully considers the processing accuracy of the equipment can be introduced and established. This model should be able to accurately reflect the geometric deviations such as powder sticking encountered by the lattice structure during the forming stage due to processing conditions, so that an accurate simulation model can be established in the early design stage. In the laser cladding process of the lattice structure, due to the operating limitations and process characteristics of the forming equipment, the rods of the lattice structure often have geometric size deviations due to different processing conditions, which are mainly manifested in the diameter of the rods. These deviations do not appear randomly, but are closely related to the relative position of the rods relative to the laser beam.

[0040] When the inclination angle of the rod is close to 90 degrees, it means that the axis of the rod is completely parallel to the direction of the laser beam. Under this ideal condition, the energy concentration of the laser beam is the highest, and the local heating of the rod is the most uniform, so the diameter of the formed rod can usually reach the maximum value. However, as the inclination angle of the rod gradually increases, the energy distribution of the laser beam on the cross section of the rod will shift and diffuse, resulting in a decrease in heat transfer efficiency, which will compress the actual solidification diameter of the rod.

[0041] When the rod is perpendicular to the direction of the laser beam, the energy utilization rate is the lowest because the laser energy cannot directly act on the normal direction of the rod. Therefore, in this extreme case, the actual diameter of the rod will be reduced to the minimum value. At the same time, when the rod diameter is small, the support rod is more easily affected by the SLM manufacturing process, making the error between the formed rod diameter and the designed rod diameter more significant; this phenomenon is due to the fact that the melting depth and the melting width of the laser molten pool are not equal during the printing process, resulting in the rod diameter being mainly affected by the melting width when the rod inclination angle is small; and the rod diameter being mainly affected by the melting depth when the rod inclination angle is large. Therefore, the actual rod diameter of the forming is closely related to the thickness of the single layer of powder laid, the laser power, and the size and shape of the laser spot of the forming equipment.

[0042] Therefore, reference Figure 1 As shown, Figure 1 Shows the existing three-dimensional object Figure 1 Actual objects of rods with different inclination angles and enlarged partial schematic diagrams.

[0043] If high-precision simulation is to be achieved, a three-dimensional model under the influence of the geometric accuracy of the equipment should be established. The laser spot parameters of SLM equipment of different brands and models, or even different batches of the same model, are different, resulting in the functional relationship between the formed rod diameter and the designed rod diameter cannot be generalized, and fine-tuning is required for specific equipment. Therefore, in order to adapt to the high-precision simulation of a variety of equipment, the position of the inclination angle-rod diameter function should be reserved when executing the three-dimensional modeling step, that is, the function is integrated into the modeling process in the form of input parameters, so that different functions can be conveniently set for different equipment during modeling.

[0044] Therefore, reference Figure 2 As shown, Figure 2 A flowchart of an exemplary method for simulating mechanical properties of a lattice structure for additive manufacturing in some embodiments of the present application is shown. The present application relates to a method for simulating mechanical properties of a lattice structure for additive manufacturing, comprising:

[0045] S1: Based on the formed three-dimensional object image containing various diameters and pillar inclinations, pixel point measurement is performed to generate the formed rod diameter.

[0046] refer to Figure 3 As shown, Figure 3A schematic diagram of an exemplary sample including various diameters and pillar inclination angles according to some embodiments of the present application is shown. In the actual implementation process, in S1, firstly, a three-dimensional object sample is designed using computer-aided design (such as CAD, SolidWorks, ProE, UG, etc.) software, and the three-dimensional object sample needs to include different diameters and pillar inclination angles, and then the three-dimensional object sample is manufactured using selective laser melting (SLM), electron beam melting (EBM) or other additive manufacturing technologies; then, an optical microscope device with a suitable microscope magnification is selected and the pixel resolution of the optical microscope device is calibrated, and each pixel length is recorded (the pixel length is calculated by dividing the known actual length by the corresponding number of pixels), and then the optical microscope device is used to take images of the pillar parts of the three-dimensional object sample with different diameters and inclination angles to generate a three-dimensional object image including a variety of diameters and pillar inclination angles; then, the image of the three-dimensional object sample is imported into an image processing software (such as Python's OpenCV or ImageJ) and the image is binarized to extract edge information, and then the pixel point measurement tool is used to obtain the pixel diameter of the sample forming rod; finally, the pixel diameter is converted into an actual diameter according to the pixel resolution of the optical microscope device (the actual diameter is calculated by multiplying the pixel diameter measured in the image by the pixel length).

[0047] S2: Take the rod diameter and inclination angle as input, the formed rod diameter as output and use the machine learning artificial neural network method for training, fit the inclination angle-rod diameter, and then predict the formed rod diameter according to the design value, and use the predicted value to establish the lattice structure model.

[0048] refer to Figure 4 As shown, Figure 4 A schematic diagram of converting a design model into a finite element simulation model according to a predicted value of a formed rod diameter in some embodiments of the present application is shown. In the actual implementation process, in S2, the overall process is as follows:

[0049] Importing module sets (libraries) for data processing, modeling, and evaluation usually includes: module sets (libraries) for reading and processing data, module sets (libraries) for machine learning algorithms and tools, and module sets (libraries) for numerical operations; for example, taking Python as an example, pandas, sklearn, numpy and other libraries are usually imported to support data reading, modeling, evaluation and other tasks.

[0050] Load data containing rod diameter and inclination characteristics and normalize the loaded data to change the data to a set fixed interval, usually within the interval [0,1]; then divide the processed data into a training set and a test set to generate a first data set containing the training set and the test set, usually with the training set accounting for 80% and the test set accounting for 20%.

[0051] When using a multi-layer perceptron (MLP) to construct a neural network regression model to fit the relationship between inclination angle and rod diameter, the data must first be preprocessed by normalization or standardization to ensure that the data is within a suitable range and to improve the convergence speed of the neural network. Secondly, the structure of the neural network is defined, including the input layer, hidden layer, and output layer. The number of neurons in the hidden layer needs to be determined experimentally. The weight and bias parameters are set by random initialization. In the forward propagation phase, the weighted input sum of each neuron is calculated and then transformed by an activation function, such as ReLU or Sigmoid, to introduce nonlinearity. The loss function uses the mean square error (MSE) to calculate the difference between the predicted value and the actual value. In the back-propagation phase, the gradient of the loss function with respect to the weights and biases is calculated, and then the parameters are updated using the gradient descent algorithm. The calculation process involves the chain rule, that is, the gradient of the loss function with respect to the activation value, the derivative of the activation function with respect to the weighted sum, and the product of the derivative of the weighted sum with respect to the weight. This process is repeated until the preset maximum number of iterations is reached, or the value of the loss function drops to a preset threshold, thereby training the neural network regression model.

[0052] After each training iteration, the test set is used to predict the trained neural network regression model and the mean square error and determination coefficient (R 2 ) is used to evaluate the model, where the mean square error is the average square error between the predicted value and the true value, and the smaller the value, the better; the determination coefficient is used to measure the goodness of fit of the model, and the closer the value is to 1, the better the model performance.

[0053] The forming rod diameter is predicted by a neural network regression model according to the design value, and then the lattice structure model is established using the predicted value.

[0054] S3: Carry out compression tests on three-dimensional compression mechanical specimens of different diameters, obtain the mechanical parameters of different diameters, and use machine learning artificial neural network methods to train and fit the diameter-mechanical parameters, establish a mechanical test model, and then predict the elastic modulus of the average forming diameter.

[0055] refer to Figure 5 As shown, Figure 5A schematic diagram of the compression process of an exemplary three-dimensional compressive mechanical specimen of some embodiments of the present application is shown. In the actual implementation process, in S3, firstly, a three-dimensional compressive mechanical specimen with different diameters is designed using computer-aided design (such as CAD, SolidWorks, ProE, UG, etc.) software, and then the three-dimensional compressive mechanical specimen is manufactured using selective laser melting (SLM), electron beam melting (EBM) or other additive manufacturing technology; then, a material testing device (such as a compression testing machine, a universal testing machine and other material mechanics testing equipment) is used to perform a mechanical compression test on the three-dimensional compressive mechanical specimens of different diameters and record the experimental results including the compression load (the force applied during the compression process) and the displacement value (the deformation of the specimen during the compression process), generate a stress-strain curve, and then calculate the elastic modulus according to the experimental results: Where E is the elastic modulus, ΔF is the load increment per unit length, A is the cross-sectional area of ​​the three-dimensional compression mechanics specimen, Δu is the displacement increment in the loading direction, and L is the initial height of the three-dimensional compression mechanics specimen; in this way, the diameter of each three-dimensional compression mechanics specimen, the matching elastic modulus and other mechanical parameters required by the experimenter are recorded to generate the corresponding mechanical data table; when calculating the elastic modulus, the corresponding yield strength and compressive strength can also be calculated.

[0056] Then, the mechanical data table is used as the second data set for machine learning to be trained using the machine learning artificial neural network method. The specific process is as follows:

[0057] Importing module sets (libraries) for data processing, modeling, and evaluation usually includes: module sets (libraries) for reading and processing data, module sets (libraries) for machine learning algorithms and tools, and module sets (libraries) for numerical operations; for example, taking Python as an example, pandas, sklearn, numpy and other libraries are usually imported to support data reading, modeling, evaluation and other tasks.

[0058] The above-mentioned mechanical data table containing diameter and elastic modulus characteristics is loaded and all the data therein is normalized to change the data to a set fixed interval, usually in the range of [0,1]; the processed data is then divided into a training set and a test set to generate a second data set containing the training set and the test set, usually with the training set accounting for 80% and the test set accounting for 20%.

[0059] A multi-lateral perceptron (MLP) is used to construct a neural network regression model to fit the diameter-mechanical parameters, wherein the average error is used as the loss function of the neural network regression model, and then the hidden layer and the number of neurons it contains are set, and the maximum number of training iterations is set, and then the configured neural network regression model is trained through back propagation and gradient descent methods.

[0060] After each training iteration, the test set is used to predict the trained neural network regression model and the mean square error (MSE) and determination coefficient (R) are calculated based on the prediction results. 2 ), and perform model evaluation. The mean square error calculation formula is: The formula for calculating the coefficient of determination is: where y i is the ith true value, is the i-th predicted value, n is the number of samples, is the average of the true values.

[0061] The neural network regression model with the mean square error and determination coefficient reaching the values ​​set by the experimenter is set as the mechanical test model, and then the elastic modulus of the average forming diameter is predicted based on the mechanical test model.

[0062] S4: According to the lattice structure model and the mechanical test model, a finite element simulation model is established and the predicted elastic modulus value is input into the finite element simulation model as a material parameter to perform a mechanical property analysis, and then the finite element simulation model is adjusted and fitted according to the generated mechanical property analysis results.

[0063] In the actual implementation process, in S4, the model file is first imported into the finite element software ABAQUS.

[0064] Then, set the material properties: among them, set the basic properties, plastic properties, rate-dependent properties and damage properties of the material, including the density, elastic modulus, Poisson's ratio, stress, strain, damage parameter and damage evolution of the material; in this application, refer to the JC constitutive model to define the material: (T * ) m ], where σ is the equivalent flow stress, is the equivalent plastic strain, is the equivalent plastic strain rate, is the equivalent plastic strain rate, T m is the dimensionless temperature and is calculated as Where T ref is the reference temperature, T melt is the melting temperature, A is the initial yield stress, B is the hardening modulus, n is the hardening exponent, C is the strain rate hardening parameter, and m is the temperature softening exponent.

[0065] For example, the material density is set to 4.88324e-09, the elastic modulus is set to 125443, the Poisson's ratio is set to 0.342, the plastic properties of the material are set to 860, 450, 0.325, 1, 1650, 1400 (where 860 is the initial yield stress, 450 is the strain corresponding to the stress, 0.325 and 1 are other plastic parameters of the material hardening defined by the specific software, and 1650 and 1400 are further yield stress and strain points), and the rate-dependent properties of the material are set to 0.019 and 0.011 (where 0.019 and 0.011 are is a constant parameter related to the strain rate), the damage parameters of the material are set to 0.221, 32.332, 12.814, 1, 1, 0, 0, 1 (where 0.221 is the initial damage value, 32.332 and 12.814 are damage strains or damage initiation parameters, 1, 1 are damage evolution control parameters, 0, 0 are damage influence parameters, and 1 is the end value of the damage parameter), and the damage evolution of the material is set to 0.08*Meshsize*0.5 (where 0.08 is the damage evolution proportional factor, Meshsize is the mesh size, and 0.5 is the adjustment factor for controlling the damage evolution speed and distribution).

[0066] Then, the dynamics analysis parameters are set, including analysis step size, mass scaling, target time increment, field output and history output type, etc.

[0067] Then, the model is assembled: the lattice structure model is meshed, corresponding material sections are assigned to various parts of the structure, and the mechanical test simulation model and the fixture are assembled together according to the corresponding position relationship to form a complete finite element simulation model.

[0068] Then, define the loads and boundary conditions for the finite element simulation model: define the external loads and boundary conditions that the structure is subject to in the dynamic analysis, including general contact, displacement value of the indenter, completely fixed constraint at the bottom, etc. In order to make the simulation process consistent with the actual experimental process, this part requires the test personnel to ensure the accuracy and rationality of the loads and boundary conditions.

[0069] Thus, the construction of the finite element simulation model is completed, and the predicted elastic modulus value is input into the finite element simulation model as a material parameter to perform mechanical property analysis and generate mechanical property analysis results.

[0070] refer to Figure 6-Figure 12 As shown, Figure 6 A schematic diagram showing an exemplary mechanical simulation result of some embodiments of the present application, Figure 7 A schematic diagram showing exemplary mechanical test results of some embodiments of the present application, Figure 8A schematic diagram showing an exemplary mechanical experiment and simulation comparison of some embodiments of the present application is shown; Fig. 9 A schematic diagram of a kinetic energy-internal energy curve of an exemplary simulation process of some embodiments of the present application is shown; Fig.10 A schematic diagram showing a comparison between an exemplary simulation method of the present application and experimental results of some embodiments of the present application is shown; Fig.11 A schematic diagram showing a comparison between an exemplary simulation method of the present application and an uncorrected simulation in some embodiments of the present application is shown; Fig.12 An exemplary simulation method of the present application, experimental results and a comparison diagram of uncorrected simulations of some embodiments of the present application are shown.

[0071] Furthermore, the generated mechanical properties analysis results are compared with the actual experimental data to generate error results.

[0072] Perform error analysis based on the error results and define an error function based on the difference between the quantified experimental value and the simulated value;

[0073] For example, the error function is defined as: Where N is the number of data, σ sim,i is the stress of the simulated value, σ exp,i is the experimental stress value.

[0074] According to the error function, the parameters of the finite element simulation model are adjusted; if the error between the simulation result and the experimental result is large, the geometric parameters and material parameters can be adjusted.

[0075] The finite element simulation model is optimized to minimize the error function by iterating the number of times set by the experimenter.

[0076] Therefore, each time the finite element simulation model is optimized, the mechanical properties analysis is performed again using the optimized finite element model.

[0077] In some embodiments of the present application, reference Fig.13 As shown, Fig.13 The schematic diagram of the structure of an exemplary lattice structure mechanical performance simulation system for additive manufacturing of some embodiments of the present application is shown. The present application also relates to a lattice structure mechanical performance simulation system for additive manufacturing, comprising:

[0078] A lattice structure mechanical properties simulation device for additive manufacturing using the above simulation method.

[0079] Additive manufacturing equipment is used to form three-dimensional objects and three-dimensional compression mechanics specimens using additive manufacturing technology.

[0080] Among them, additive manufacturing equipment such as selective laser melting (SLM) and electron beam melting (EBM) are usually included, which form three-dimensional objects by stacking materials layer by layer. Its core principle is to use powder or solid materials to manufacture parts layer by layer according to three-dimensional model data, which is suitable for the processing of complex structures, such as specimens with various diameters and pillar inclinations. Additive manufacturing equipment usually includes key components such as powder supply system, forming chamber, laser or electron beam emitter, multi-axis platform, etc.

[0081] Light microscope equipment, used to capture images.

[0082] Among them, the optical microscope equipment, that is, the optical microscope, is a device that uses an optical system to magnify and observe the sample. By photographing the surface structure of the sample, the geometric dimensions (such as diameter and inclination) of the additively manufactured sample can be obtained.

[0083] Material testing equipment, used to conduct material mechanics tests.

[0084] Among them, material testing equipment is an instrument used to evaluate the mechanical properties of samples, usually including compression testing machines, tensile testing machines, fatigue testing machines or universal testing machines. In this application, a compression testing machine is used to perform compression testing on additive samples to evaluate their elastic modulus, yield strength and other parameters, and it can clamp and load non-standard samples (such as additive manufacturing samples), and then calculate relevant mechanical parameters through real-time collected load-displacement curve data.

[0085] In some embodiments of the present application, a lattice structure mechanical properties simulation device for additive manufacturing using the above-mentioned simulation method includes:

[0086] An image processing module is used to measure pixels and generate a formed rod diameter based on a formed three-dimensional object image including various diameters and pillar inclinations;

[0087] The first training module is used to take the rod diameter and the inclination angle as input, take the formed rod diameter as output, and use the machine learning artificial neural network method to train, fit the inclination angle-rod diameter, and then predict the formed rod diameter according to the design value, and use the predicted value to establish a lattice structure model;

[0088] The second training module is used to perform compression tests on three-dimensional compression mechanical specimens of different diameters, obtain mechanical parameters of different diameters, and use machine learning artificial neural network methods to train and fit diameter-mechanical parameters, establish a mechanical test model, and then predict the elastic modulus of the average forming diameter;

[0089] The finite element simulation module is used to establish a finite element simulation model based on the lattice structure model and the mechanical test model, and input the predicted elastic modulus value as a material parameter into the finite element simulation model to perform mechanical property analysis, and then adjust and fit the finite element simulation model according to the generated mechanical property analysis results.

[0090] In some embodiments of the present application, reference Fig.14 As shown, Fig.14 The structural diagram of an exemplary electronic device of some embodiments of the present application is shown. The electronic device includes: a memory 201 and a processor 202, and the memory 201 stores a computer program that can be run on the processor 202. When the processor 202 executes the computer program, the method in the above embodiment is implemented. The number of the memory 201 and the processor 202 can be one or more.

[0091] The electronic device also includes:

[0092] The communication interface 203 is used to communicate with external devices and perform data exchange transmission.

[0093] If the memory 201, the processor 202 and the communication interface 203 are implemented independently, the memory 201, the processor 202 and the communication interface 203 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.14 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0094] Optionally, in a specific implementation, if the memory 201, the processor 202 and the communication interface 203 are integrated on a chip, the memory 201, the processor 202 and the communication interface 203 can communicate with each other through an internal interface.

[0095] The embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present application when the program is executed by the processor 202.

[0096] The embodiment of the present application also provides a chip, which includes a processor 202, which is used to call and execute instructions stored in the memory 201 from the memory 201, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.

[0097] The embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor 202 and a memory 201. The input interface, the output interface, the processor 202 and the memory 201 are connected through an internal connection path. The processor 202 is used to execute the code in the memory 201. When the code is executed, the processor 202 is used to execute the method provided in the embodiment of the application.

[0098] It should be understood that the processor 202 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor 202 that supports the Advanced RISC Machines (ARM) architecture.

[0099] Further, the above-mentioned memory 201 may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory 201 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0100] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0101] The above is only a specific implementation 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 method for simulating mechanical properties of lattice structures for additive manufacturing, characterized in that: The method comprises: Based on the formed three-dimensional object image containing various diameters and pillar inclinations, pixel point measurement is performed to generate the formed rod diameter; The rod diameter and inclination angle are used as input, the formed rod diameter is used as output, and the machine learning artificial neural network method is used for training to fit the inclination angle-rod diameter, and then the formed rod diameter is predicted according to the design value, and the lattice structure model is established using the predicted value; Compression tests were performed on three-dimensional compression mechanical specimens of different diameters to obtain mechanical parameters of different diameters and use machine learning artificial neural network methods to train and fit diameter-mechanical parameters, establish a mechanical test model, and then predict the elastic modulus of the average forming diameter; According to the lattice structure model and the mechanical test model, a finite element simulation model is established and the predicted elastic modulus value is input into the finite element simulation model as a material parameter to perform a mechanical property analysis, and then the finite element simulation model is adjusted and fitted according to the generated mechanical property analysis results.

2. The simulation method according to claim 1, characterized in that: When generating a formed rod diameter, the method includes: Use additive manufacturing to form three-dimensional objects with various diameters and pillar inclinations; Using an optical microscope device to photograph the three-dimensional object to generate a three-dimensional object image including a variety of diameters and pillar inclination angles; Binarizing the three-dimensional object image and obtaining the pixel diameter of the formed rod; According to the pixel resolution of the optical microscope equipment, the pixel diameter is converted into the actual diameter to generate the formed rod diameter.

3. The simulation method according to claim 2, characterized in that: When using a machine learning artificial neural network method for training, the method includes: Importing blocksets that implement data processing, modeling, and evaluation; Loading data containing rod diameter and inclination angle features and normalizing the data to generate a first data set containing a training set and a test set; Using a multi-layer perceptron to construct a neural network regression model to fit the inclination angle-rod diameter and setting neural network parameters and the number of iterations, and then using a training set to train the neural network regression model; The test set is used to predict the trained neural network regression model and calculate the mean square error and determination coefficient for model evaluation; The forming rod diameter is predicted by a neural network regression model according to the design value, and then the lattice structure model is established using the predicted value.

4. The simulation method according to claim 1, characterized in that: When obtaining mechanical parameters of different diameters, the method includes: Use additive manufacturing technology to form three-dimensional compression mechanical specimens with different diameters; Use material testing equipment to conduct mechanical compression tests on three-dimensional compression mechanical specimens with different diameters and record the experimental results including compression load and displacement values; The elastic modulus is calculated according to the experimental results and mechanical data is generated according to the diameter of each three-dimensional compression mechanical specimen and the matching elastic modulus.

5. The simulation method according to claim 4, characterized in that: When using a machine learning artificial neural network method for training, the method includes: Importing blocksets that implement data processing, modeling, and evaluation; Loading data containing diameter and elastic modulus features and normalizing the data to generate a second data set containing a training set and a test set; Using a multi-layer perceptron to construct a neural network regression model to fit the diameter-mechanical parameters and set the neural network parameters and the number of iterations, and then using a training set to train the neural network regression model; The test set is used to predict the trained neural network regression model and calculate the mean square error and determination coefficient for model evaluation; The neural network regression model that meets the preset requirements is set as the mechanical test model, and then the elastic modulus of the average forming diameter is predicted based on the mechanical test model.

6. The simulation method according to claim 3 or 5, characterized in that: When importing a library implementing data processing, modeling and evaluation, the method includes: Import the set of modules that provide data reading and data processing; Import a set of modules that provide machine learning algorithms and tools; Imports a set of blocks for numerical operations.

7. The simulation method according to claim 3 or 5, characterized in that: When the training set is used to train the neural network regression model, the method includes: Use the average error as the loss function of the neural network regression model; Set the number of hidden layers and neurons they contain and set the maximum number of training iterations; The model parameters are optimized using back-propagation and gradient descent methods.

8. The simulation method according to claim 3 or 5, characterized in that: When establishing a finite element simulation model, the method includes: Set material properties; Setting dynamics analysis parameters, including analysis step size, mass scaling, target time increment, field output, and history output type; The lattice structure model is meshed and assembled into a mechanical test model to form a finite element simulation model; Define the external loads and boundary conditions to which the structure will be subjected in the dynamics analysis.

9. The simulation method according to claim 8, characterized in that: When setting material properties, the method includes: Set basic material properties, including material density, elastic modulus, and Poisson's ratio; Set the plastic properties of the material, including stress and strain; Set rate-dependent properties of materials; Set material damage properties, including damage parameters and damage evolution.

10. The simulation method according to claim 1 or 9, characterized in that: When adjusting and fitting the finite element simulation model according to the generated mechanical property analysis results, the method includes: Compare the generated mechanical properties analysis results with the actual experimental data to generate error results; Perform error analysis based on the error results and define an error function based on the difference between the quantified experimental value and the simulated value; According to the error function, adjusting the parameters of the finite element simulation model; The finite element simulation model is optimized in an iterative cycle to minimize the error function.

11. A lattice structure mechanical properties simulation device for additive manufacturing using the simulation method according to any one of claims 1 to 10, characterized in that: include: An image processing module is used to measure pixels and generate a formed rod diameter based on a formed three-dimensional object image including various diameters and pillar inclinations; The first training module is used to take the rod diameter and the inclination angle as input, take the formed rod diameter as output, and use the machine learning artificial neural network method to train, fit the inclination angle-rod diameter, and then predict the formed rod diameter according to the design value, and use the predicted value to establish a lattice structure model; The second training module is used to perform compression tests on three-dimensional compression mechanical specimens of different diameters, obtain mechanical parameters of different diameters, and use machine learning artificial neural network methods to train and fit diameter-mechanical parameters, establish a mechanical test model, and then predict the elastic modulus of the average forming diameter; The finite element simulation module is used to establish a finite element simulation model based on the lattice structure model and the mechanical test model, and input the predicted elastic modulus value as a material parameter into the finite element simulation model to perform mechanical property analysis, and then adjust and fit the finite element simulation model according to the generated mechanical property analysis results.

12. A lattice structure mechanical properties simulation system for additive manufacturing comprising the simulation device according to claim 11, characterized in that: Also includes: Additive manufacturing equipment for forming three-dimensional objects and three-dimensional compression mechanical specimens using additive manufacturing technology; Light microscope equipment for capturing images; Material testing equipment, used to conduct material mechanics tests.

Images