Composite truss structure-process-manufacturing equipment integrated simulation method, system, equipment, medium and product

Abstract

The invention discloses a composite material truss structure-process-manufacturing equipment integrated simulation method, system, equipment, medium and product, and relates to the field of civil spacecraft on-orbit manufacturing, the method comprises the following steps: obtaining parameters of three sub-subjects of geometric structure, process and manufacturing equipment, and according to the parameters corresponding to the three sub-subjects and corresponding performance parameters, calculating the performance parameters of the three sub-subjects; the method comprises the steps of constructing a corresponding agent model based on a neural network, constructing an optimization model by adopting a collaborative optimization algorithm according to the agent model, constructing a collaborative optimization workflow based on an Isight model according to the optimization model and the agent model, and finally performing integration based on a QT platform to obtain a composite truss structure-process-manufacturing equipment integrated simulation platform. And integrated simulation is carried out. According to the method, the simulation analysis efficiency can be improved, various simulation software is integrated, the key design parameters are efficiently and accurately iteratively optimized, the optimization scheme meeting the requirements is rapidly generated, and then the overall efficiency and accuracy of analog simulation are improved.

Description

Technical Field

[0001] The present application relates to the field of on-orbit manufacturing of civil spacecraft, and specifically to a composite material truss structure-process-manufacturing equipment integrated simulation method, system, equipment, medium and product. Background Art

[0002] In recent years, with the increasing requirements for satellite signal accuracy, the size of satellite antennas has also been increasing. As the supporting structure of satellite antennas, composite trusses are an important part of spacecraft. As the size of satellite antennas continues to increase, their structural dimensions also increase accordingly. However, the size and weight of launch vehicles are strictly limited. The traditional ground manufacturing and on-orbit deployment mode can no longer meet the design and manufacturing needs of large-size composite trusses. On-orbit additive manufacturing technology has become the key to breaking through the bottleneck of traditional satellite composite truss manufacturing.

[0003] On-orbit additive manufacturing technology relies on spacecraft to transport processing equipment and raw materials to the space environment, and complete manufacturing and assembly in the space environment. This requires the integrated design of processing equipment and processing technology while designing the composite truss. The on-orbit manufacturing process involves many disciplines, with high dimensions of design variables and strong coupling. To this end, an integrated design system of structure-process-manufacturing equipment is needed to support the design and manufacturing process of composite trusses. In the integrated design process, design schemes are constantly iterated, design constraints and optimization goals change dynamically, and traditional design methods rely on simulation software, manual iterations, and coordination between disciplines, resulting in time-consuming design process scheme evaluation and calculation, and complex scheme iteration processes. Specifically, it faces the following difficulties:

[0004] 1. The traditional method adopts the form of single-discipline optimization design + multi-discipline coordination in the design of composite trusses, which has low scheme iteration efficiency and long design cycle.

[0005] 2. The working environment of composite trusses is complex and the working conditions are extreme. Some mechanism models are not yet clear and there is a lack of simulation software tools, so the performance of the scheme can only be evaluated by experiments.

[0006] 3. The composite truss design process relies on numerous third-party CAD, CAE, and database software, and lacks support from integrated design tools.

[0007] Therefore, there is an urgent need to provide a new integrated simulation method or system for composite truss structure-process-manufacturing equipment to improve the overall efficiency and accuracy of composite truss design. Summary of the invention

[0008] The purpose of this application is to provide a composite material truss structure-process-manufacturing equipment integrated simulation method, system, equipment, medium and product, which can improve the efficiency of simulation analysis, integrate various simulation software, efficiently and accurately iteratively optimize key design parameters, and quickly generate optimization solutions that meet the requirements, thereby improving the overall efficiency and accuracy of simulation.

[0009] To achieve the above objectives, this application provides the following solutions:

[0010] In a first aspect, the present application provides a composite material truss structure-process-manufacturing equipment integrated simulation method, comprising:

[0011] Obtaining parameters and performance parameters corresponding to three sub-disciplines; the three sub-disciplines are truss structure, process and manufacturing equipment; the parameters include: geometric structure parameters, process parameters and manufacturing equipment parameters; the performance parameters include: structural performance, process performance and manufacturing equipment performance;

[0012] According to the corresponding parameters of the three sub-disciplines and the corresponding performance parameters, the corresponding agent models are constructed based on neural networks; the agent models include geometric structure agent model, process agent model and manufacturing equipment agent model; the geometric structure agent model takes geometric structure parameters as input and structural performance as output; structural performance includes: stress, strain and mode; the process agent model takes process parameters as input and process performance as output; process performance includes: product strength, straightness and surface roughness; the manufacturing equipment agent model takes manufacturing equipment parameters as input and manufacturing equipment performance as output; manufacturing equipment performance includes: size, mass and energy consumption of manufacturing equipment;

[0013] According to the proxy models corresponding to the three sub-disciplines, corresponding optimization algorithms are used to construct corresponding optimization models; the optimization algorithms include: collaborative optimization algorithms; the optimization models include: geometric structure optimization model, process optimization model and manufacturing equipment optimization model; the geometric structure optimization model takes the geometric structure parameters as input, the structural mechanical properties as constraints, and the output of the geometric structure proxy model as the optimization target; the process optimization model takes the process parameters as input, the strength design requirements as constraints, and the output of the process proxy model as the optimization target; the manufacturing equipment optimization model takes the manufacturing equipment parameters as input, the equipment capability limit range, the manufacturing process compatibility and the structural mechanical properties as constraints, and the output of the manufacturing equipment proxy model as the optimization target;

[0014] According to the optimization model and the proxy model, a collaborative optimization workflow is constructed based on an Isight model;

[0015] According to the collaborative optimization workflow, integration is performed based on the QT platform to obtain an integrated simulation platform for composite truss structure-process-manufacturing equipment;

[0016] According to the composite material truss structure-process-manufacturing equipment integrated simulation platform, composite material truss structure-process-manufacturing equipment integrated simulation is performed.

[0017] Optionally, the geometric structure parameters include: total length of the truss, cross-sectional dimensions of the truss, thickness of the main beam and the longitudinal beam, width of the main beam and the longitudinal beam, strip pitch and pitch angle, strip thickness and strip width;

[0018] The process parameters include: pulling speed, forming pressure, heating and cooling temperature, winding parameters and main beam and longitudinal beam width;

[0019] The manufacturing equipment parameters include: motor parameters, mold parameters, roller parameters, heating device parameters and main beam and longitudinal beam widths.

[0020] Optionally, the step of obtaining parameters corresponding to the three sub-disciplines also includes:

[0021] Construct geometry database, process database, manufacturing equipment database, equipment library and model library;

[0022] The geometric structure database is used to store geometric structure parameters and corresponding structural performance;

[0023] The process database is used to store process parameters and corresponding process performance;

[0024] The manufacturing equipment database is used to store manufacturing equipment models and corresponding manufacturing equipment performance;

[0025] The equipment warehouse is used to store motors, tensioning equipment, heating equipment, cooling equipment, winding equipment and welding equipment;

[0026] The model library is used to store the geometry optimization model, the process optimization model, the manufacturing equipment optimization model, the geometry proxy model, the process proxy model, the manufacturing equipment proxy model, the neural network and the optimization algorithm.

[0027] Optionally, the step of constructing a collaborative optimization workflow based on an Isight model according to the optimization model and the proxy model specifically includes:

[0028] Get Task components based on the interface of the Isight model;

[0029] In the Task component, a reading component is used to read parameters; the reading component includes: 2 DataExchanger components, 2 Calculator components and 1 Optimization component; the three components are arranged from left to right, and components of the same type are parallel;

[0030] In the Optimization component, the MATLAB component with added optimization algorithm is used to build and optimize the agent model.

[0031] Optionally, the interface body of the composite material truss structure-process-manufacturing equipment integrated simulation platform includes: a parameter selection and setting area, a main function area and a result display area;

[0032] The parameter selection and setting area is used to determine the parameters;

[0033] The main function area is used to select functions;

[0034] The result display area is used to display pictures and simulation results.

[0035] Optionally, the parameter selection and setting area is constructed using a TreeWidget control of a QT platform.

[0036] In a second aspect, the present application provides a composite material truss structure-process-manufacturing equipment integrated simulation system, the composite material truss structure-process-manufacturing equipment integrated simulation system comprising:

[0037] A parameter acquisition module is used to acquire parameters and performance parameters corresponding to three sub-disciplines; the three sub-disciplines are truss structure, process and manufacturing equipment; the parameters include: geometric structure parameters, process parameters and manufacturing equipment parameters; the performance parameters include: structural performance, process performance and manufacturing equipment performance;

[0038] The agent model building module is used to build the corresponding agent model based on the neural network according to the corresponding parameters of the three sub-disciplines and the corresponding performance parameters; the agent model includes a geometric structure agent model, a process agent model and a manufacturing equipment agent model; the geometric structure agent model takes the geometric structure parameters as input and the structural performance as output; the structural performance includes: stress, strain and mode; the process agent model takes the process parameters as input and the process performance as output; the process performance includes: the strength, straightness and surface roughness of the product; the manufacturing equipment agent model takes the manufacturing equipment parameters as input and the manufacturing equipment performance as output; the manufacturing equipment performance includes: the size, mass and energy consumption of the manufacturing equipment;

[0039] The optimization model construction module is used to construct the corresponding optimization model according to the proxy models corresponding to the three sub-disciplines by using the corresponding optimization algorithms; the optimization algorithms include: collaborative optimization algorithm; the optimization models include: geometric structure optimization model, process optimization model and manufacturing equipment optimization model; the geometric structure optimization model takes the geometric structure parameters as input, the structural mechanical properties as constraints, and the output of the geometric structure proxy model as the optimization target; the process optimization model takes the process parameters as input, the strength design requirements as constraints, and the output of the process proxy model as the optimization target; the manufacturing equipment optimization model takes the manufacturing equipment parameters as input, the equipment capability limit range, the manufacturing process compatibility and the structural mechanical properties as constraints, and the output of the manufacturing equipment proxy model as the optimization target;

[0040] A collaborative optimization workflow construction module, used to construct a collaborative optimization workflow based on the Isight model according to the optimization model and the proxy model;

[0041] A simulation platform integration module, which is used to integrate the collaborative optimization workflow based on the QT platform to obtain a composite material truss structure-process-manufacturing equipment integrated simulation platform;

[0042] The simulation module is used to perform composite material truss structure-process-manufacturing equipment integrated simulation based on the composite material truss structure-process-manufacturing equipment integrated simulation platform.

[0043] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the integrated simulation method of the composite truss structure-process-manufacturing equipment.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the composite material truss structure-process-manufacturing equipment integrated simulation method.

[0045] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the composite material truss structure-process-manufacturing equipment integrated simulation method.

[0046] According to the specific embodiments provided in this application, this application has the following technical effects:

[0047] The present application provides a composite truss structure-process-manufacturing equipment integrated simulation method, system, equipment, medium and product. By combining the use of proxy models and collaborative optimization algorithms, complex simulation analysis optimization is transformed into a multidisciplinary optimization problem. The proxy model technology is applied to the simulation process to speed up the iterative optimization of data. This can solve the problem of high parameter coupling between disciplines of composite trusses. The present application constructs a proxy model through a neural network, speeds up the iterative optimization of data, and solves problems such as the long design cycle of traditional solutions; it realizes the integrated simulation of the structure-process-manufacturing equipment of the entire composite truss, and provides tool support for on-orbit manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 This is a schematic flow chart of a composite material truss structure-process-manufacturing equipment integrated simulation method according to an embodiment of the present application;

[0050] Figure 2 This is a flow chart of a composite material truss structure-process-manufacturing equipment integrated simulation system according to an embodiment of the present application.

[0051] Figure 3 This is a diagram of the agent model training process according to an embodiment of the present application;

[0052] Figure 4 This is a collaborative optimization algorithm framework diagram in one embodiment of the present application;

[0053] Figure 5 This is a diagram of a collaborative optimization workflow structure in accordance with an embodiment of the present application;

[0054] Figure 6 This is a schematic diagram of the interface of the integrated platform according to an embodiment of the present application;

[0055] Figure 7 This is a schematic diagram of the structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0058] In an exemplary embodiment, Figure 1 As shown, a composite material truss structure-process-manufacturing equipment integrated simulation method is provided, which specifically includes:

[0059] S1: Obtain parameters and performance parameters corresponding to three sub-disciplines; the three sub-disciplines are truss structure, process and manufacturing equipment; the parameters include: geometric structure parameters, process parameters and manufacturing equipment parameters; the performance parameters include: structural performance, process performance and manufacturing equipment performance.

[0060] Specifically, the geometric structure parameters are shown in Table 1:

[0061] Table 1 Geometric structure parameters

[0062]

[0063]

[0064] Among them, the truss cross-sectional dimension variables directly affect the bearing capacity and stiffness of the truss, and its value range should meet the strength requirements, space and weight restrictions; the two variables of longitudinal beam thickness and width directly affect the stability and bearing capacity of the overall structure, and should take the smallest value while ensuring the strength and performance requirements to reduce costs; the strip pitch / pitch angle variables affect the overall shape and mechanical properties of the structure; the strip width and thickness also affect the mechanical properties and structural weight of the entire structure as a whole.

[0065] The process parameters are shown in Table 2:

[0066] Table 2 Process parameters

[0067] Serial number Variable Name <![CDATA[x8]]> Traction speed <![CDATA[x9]]> Forming pressure <![CDATA[x 10 ]]> Heating / cooling temperature <![CDATA[x 11 ]]> Winding parameters <![CDATA[x4]]> (Main beam) longitudinal beam width

[0068] Among them, the process parameters are divided into three parts: main beam process parameters, inclined beam process parameters and welding process parameters. The processing temperature and speed variables of the main beam process parameters and the processing temperature and speed variables of the inclined beam process parameters are directly related to the quality and performance of the structure, and their value ranges are determined according to the characteristics of the materials used and the structural requirements; the welding temperature and speed variables of the welding process parameters affect the stability and durability of the structural connection parts, and their value ranges are determined according to the welding materials and technical limitations.

[0069] The manufacturing equipment parameters are shown in Table 3:

[0070] Table 3 Manufacturing equipment parameters

[0071]

[0072]

[0073] Among them, the manufacturing equipment parameters are mainly the equipment and machinery used in manufacturing trusses. The parameters include speed, accuracy, and strength, which can ensure processing efficiency and quality at the same time; the width of the (main beam) longitudinal beam will also affect the parameters of its processing equipment. The goal of manufacturing equipment parameters is to reasonably configure parameters, adjust manufacturing equipment, and reduce costs.

[0074] S2: According to the corresponding parameters of the three sub-disciplines and the corresponding performance parameters, the corresponding agent model is constructed based on the neural network.

[0075] S2 specifically includes:

[0076] S21: Based on the BP neural network, construct the corresponding agent models for the three sub-disciplines respectively. Specifically, determine the structural parameters of the agent model according to the sample data volume and design experience, such as the number of input and output layer nodes, the number of hidden layers, the number of hidden layer nodes, the learning rate, etc.

[0077] The BP neural network is used to construct a geometric structure proxy model, and the mapping relationship between input variables and output variables is learned. The input and output table of the geometric structure proxy model is shown in Table 4:

[0078] Table 4. Input and output table of geometric structure proxy model

[0079] Input variables serial number Output variables serial number Truss total length <![CDATA[x1]]> stress <![CDATA[y1]]> Truss section size <![CDATA[x2]]> strain <![CDATA[y2]]> (Main beam) longitudinal beam thickness <![CDATA[x3]]> Modal <![CDATA[y3]]> (Main beam) longitudinal beam width <![CDATA[x4]]> Strip pitch / pitch angle <![CDATA[x5]]> Strip thickness <![CDATA[x6]]> Strip width <![CDATA[x7]]>

[0080] The geometric structure proxy model is constructed based on the input and output variables. The parameter table of the geometric structure proxy model is shown in Table 5:

[0081] Table 5 Geometric structure proxy model parameters

[0082]

[0083]

[0084] For process parameters, the underlying mechanism of the mapping relationship between stiffness and strength and process parameters is not clear, so a proxy model is used for fitting. The input and output table of the process proxy model is shown in Table 6:

[0085] Table 6 Process proxy model input and output table

[0086] Input variables serial number Output variables serial number Traction speed <![CDATA[x8]]> strength <![CDATA[y4]]> Forming pressure <![CDATA[x9]]> Straightness <![CDATA[y5]]> Heating / cooling temperature <![CDATA[x 10 ]]> Surface roughness <![CDATA[y6]]> Winding parameters <![CDATA[x 11 ]]> (Main beam) longitudinal beam width <![CDATA[x4]]>

[0087] The process proxy model is constructed based on the input and output variables. The process proxy model parameter table is shown in Table 7:

[0088] Table 7 Process proxy model parameters

[0089]

[0090] The required manufacturing equipment parameters are determined according to the geometric structure parameters and process parameters. The input and output table of the manufacturing equipment proxy model is shown in Table 8:

[0091] Table 8 Manufacturing equipment proxy model input and output table

[0092] Input variables serial number Output variables serial number Motor parameters <![CDATA[x 12 ]]> Manufacturing equipment size <![CDATA[y7]]> Mould parameters <![CDATA[x 13 ]]> Manufacturing equipment quality <![CDATA[y8]]> Roller parameters <![CDATA[x 14 ]]> Energy consumption of manufacturing equipment <![CDATA[y9]]> Heating device parameters <![CDATA[x 15 ]]> (Main beam) longitudinal beam width <![CDATA[x4]]>

[0093] The manufacturing equipment proxy model is constructed based on the input and output variables. The manufacturing equipment proxy model parameter table is shown in Table 9:

[0094] Table 9 Manufacturing equipment proxy model parameters

[0095]

[0096] S22: Train and test the proxy model. Specifically, Figure 3 As shown in the figure, after the proxy model is built, the proxy model is trained with sample data. Through layer-by-layer iterative optimization, the model continuously adjusts and updates the weights. After reaching the parameters that meet the target requirements, a model with high accuracy for solving the spatial composite material truss is obtained. Finally, the model is tested to complete the construction of the sub-discipline proxy model.

[0097] Specifically, the BP neural network model is used to construct a sub-discipline proxy model to replace CAE software to quickly evaluate the performance of the current simulation solution and speed up the optimization design iteration. The BP neural network (Back Propagation Artificial Neural Network) consists of an input layer, a hidden layer, and an output layer. The entire BP neural network is divided into three parts, namely forward propagation, back propagation, and test model.

[0098] In the neural network perceptron x1,x2,x3,…,x i are input nodes; w1,w2,w3,…,w i is the weight, each w represents the influence ratio of the output of the previous layer on the input data of the next layer; b is the bias, which can ensure that the activation function works in the nonlinear region, thereby improving the nonlinear expression ability of the model, increasing the flexibility of the model, and ensuring that when the input is zero, the output of the neuron is also guaranteed to be non-zero; f is the activation function, which can nonlinearly map the output of the previous layer to a real number between 0 and 1, thereby increasing the expression ability of the model; output is the output node. In the BP neural network, the signal is forward propagated and the error is backward propagated.

[0099] The data x is input into the first layer of neural network, the eigenvalue is obtained by feature extraction, and the output of the first layer of neurons is obtained by weight and bias calculation; the output of the first layer of neurons is mapped to a real number between 0 and 1 through the activation function, i.e., the sigmoid function, and the mapped real number is used as the input of the second layer of neurons. The optimization is iterated layer by layer to obtain the final output. This process is called forward propagation.

[0100] Compare the result with the expected output, and perform back propagation if not satisfied. In the BP neural network, the loss function is the mean square error between the output value and the expected value. When performing back propagation, the Adam gradient descent method is used to solve it. In essence, the loss function is adjusted along the direction of gradient descent by derivation, and the optimization is iterated step by step to finally obtain the lowest point of the loss function, that is, the point with the minimum error. In this application, the learning rate is 0.001 and the training is 1000 generations.

[0101] This application uses a fully connected neural network. The training process requires adjustment of hyperparameters such as the neural network structure, optimizer, and activation function to determine the optimal hyperparameter combination and improve the prediction accuracy of the proxy model.

[0102] S3: According to the agent models corresponding to the three sub-disciplines, the corresponding optimization algorithms are used to construct the corresponding optimization models.

[0103] S3 specifically includes:

[0104] S31: Clarify the optimization objectives, constraints, and design variables for each sub-discipline.

[0105] Geometry:

[0106] Optimization objectives: stress, strain and mode of the product.

[0107] Constraints: Structural mechanical properties.

[0108] Design variables: Geometric structure parameters, see Table 1 for details.

[0109] The layout of the geometric structure is optimized to improve the structural efficiency and manufacturability. The design optimization problem is constructed to minimize the total truss length while meeting the structural performance requirements.

[0110] Process:

[0111] Optimization objectives: product strength, straightness (section angle) and surface roughness.

[0112] Constraints: Strength design requirements.

[0113] Design variables: process parameters, see Table 2 for details.

[0114] Manufacturing equipment:

[0115] Optimization objectives: size, quality and energy consumption of manufacturing equipment.

[0116] Constraints: Equipment capability limitations, manufacturing process compatibility, and structural mechanical properties.

[0117] Design variables: manufacturing equipment parameters, see Table 3 for details.

[0118] S32: Use collaborative optimization algorithms to coordinate optimization between the system level and the discipline level to obtain simulation results that meet the requirements.

[0119] Specifically, Figure 4 As shown, this application adopts multidisciplinary optimization-cooperative optimization algorithm, and the system-level variables of each discipline Sub-discipline n design variables representing system-level requirements; The coupled variables in discipline n representing the system-level requirements; in Indicates the coupling variables that need to be optimized in this discipline, Indicates that the coupling variables determined by other disciplines do not change during the optimization process of this discipline. In the process of sub-discipline optimization, the optimized variables are (x n ,y n ),and is considered to be a fixed value. The objective function is to minimize the consistency constraint J n , that is, minimizing the subsystem-level design variable x n , coupling variable y n With system-level transfer n The difference between the variables.

[0120] like Figure 4 As shown, the subject-level optimizer 1 corresponds to Figure 5 Optimization in is the optimizer of the geometric structure proxy model; the subject-level optimizer 2 corresponds to Figure 5Optimization-1 in the example is the optimizer for the process agent model; discipline-level optimizer 3 corresponds to Figure 5 Optimization-2 in the example is the optimizer for the manufacturing equipment proxy model; the final system-level optimizer corresponds to Figure 5 The optimization algorithm in is a system-level optimizer, which coordinates the optimization results of three discipline-level optimizers.

[0121] S4: Figure 5 As shown, according to the optimization model and the proxy model, a collaborative optimization workflow is constructed based on the Isight model.

[0122] S41: Build collaborative optimization workflows.

[0123] Specifically, the collaborative optimization workflow is divided into the parameter reading part and the optimization part. For the parameter reading part, the Task component is obtained based on the interface of the Isight model to read the parameters. The Task component includes 2 Data Exchanger components, 2 Calculator components and 1 Optimization component. The three components are arranged from left to right, and the components of the same type are parallel. Finally, they are connected to complete the construction of the parameter reading part.

[0124] The optimization part is divided into system-level optimizer and discipline-level optimizer, and the two are coordinated for optimization. The Optimization component includes three MATLAB components and one Data Exchanger component. The three MATLAB components are named: 1. Structural proxy model, 2. Process proxy model, and 3. Equipment proxy model. One Data Exchanger component is named DataExchanger2. The three MATLAB components are in parallel. Add the three Optimization components in the Process Components option to the MATLAB component and name them as: Optimization Algorithm 1, Optimization Algorithm 2, and Optimization Algorithm 3. The sight model automatically recognizes MATLAB as a subcomponent of Optimization.

[0125] S42: Build the proxy model component. After building the collaborative optimization workflow, the Matlab component in the Isight model is used to read, run, and solve the neural network code.

[0126] Specifically, in the InputMappings option in the MATLAB component, establish the input variable x of the corresponding sub-discipline; read and import the proxy model code of the corresponding sub-discipline in the Commands option, and establish the output variable y of the corresponding sub-discipline in the Output Mappings option. The construction steps of the three proxy model components are consistent. After the construction of the proxy model component is completed, the corresponding optimization algorithm component will automatically identify and add variables. At this time, the corresponding variables can be selected as constraints and optimization targets in the Variables and Objectives options of the optimization algorithm component. In addition, when using Matlab to read and run the proxy model, it is necessary to import the machine learning and deep learning toolkits in Matlab, otherwise an error will be reported when running the solution and the solution cannot be obtained.

[0127] S43: The automatic configuration of the optimization model connects the parameter reading part and the optimization part. The DataExchanger component reads the external Txt document parameters and passes the parameters to the system-level optimizer through the calculator component. The system-level optimizer then passes the parameters to the discipline-level optimizer to use the proxy model for calculation and solution. This completes the construction of the entire Isight collaborative optimization workflow. The specific sub-steps are as follows:

[0128] Build corresponding databases, equipment libraries, and model libraries to store data. The database is divided into geometric structure database, process database, and manufacturing equipment database.

[0129] The geometry database is used to store geometry parameters and corresponding structure performance; the process database is used to store process parameters and corresponding process performance; the manufacturing equipment database is used to store manufacturing equipment models and corresponding manufacturing equipment performance; the equipment library is used to store motors, tensioning equipment, heating equipment, cooling equipment, winding equipment and welding equipment; the model library is used to store the geometry optimization model, the process optimization model, the manufacturing equipment optimization model, the geometry proxy model, the process proxy model, the manufacturing equipment proxy model, the neural network and the optimization algorithm.

[0130] When configuring the model, the model information and equipment library information are called from the model library, and after running the proxy model to calculate the target variables, the data is passed to the database for storage.

[0131] After completing the above steps, read the Txt path in two DataExchanger components respectively. The two components read the input variable x file and the output variable y file respectively. Separate reading is conducive to variable identification. In the Isight model, if there are too many variables, a Calculator component may not be able to identify them all. Add the respective Txt document parameters as variables in the two Data Exchanger components. The variable names should be set simple so that the Calculator component can accurately identify them. In the system-level "Optimization Algorithm" component, add the input variable x and the output variable y as variables respectively and establish an equation in the Calculator component so that the variables in the DataExchanger component are equal to the variables in the "Optimization Algorithm" component.

[0132] When the model is running, the DataExchanger component reads the content in Txt and passes it to Optimization (discipline-level optimizer) through a calculator equation. The parameters in the Optimization component configure the three sub-discipline optimizers (optimization algorithm components) in its collaborative optimization workflow. After the three neural network proxy models in MATLAB obtain data, they perform iterative optimization calculations on the data. The iteratively optimized data is transmitted to the system-level optimizer for computational simulation and passed to the DataExchanger2 component. The optimal result is output and saved in the pre-set Txt document.

[0133] In the process of building a collaborative optimization workflow, the entire optimization problem is converted into two optimization problems at the discipline level and the system level. The variables are decoupled, and a collaborative optimization algorithm is used between the system level and the discipline level to improve the overall efficiency and accuracy of composite truss design.

[0134] S5: Figure 6 As shown, according to the collaborative optimization workflow, integration is performed based on the QT platform to obtain an integrated simulation platform for composite truss structure-process-manufacturing equipment.

[0135] S5 specifically includes:

[0136] S51: Interface function design. The interface of the composite material truss structure-process-manufacturing equipment integrated simulation platform is divided into parameter selection and setting area, main function area, and result display area. The parameter selection and setting area is used to determine the parameters; the main function area is used to select functions; and the result display area is used to display pictures and simulation results.

[0137] Specifically, users can select corresponding parameters in the parameter selection and setting area, such as the input variables and output variables of the geometric structure proxy model. Users can also edit and save and update the initial values, maximum values, and minimum values ​​of the corresponding parameters of the three sub-disciplines of geometry, process, and manufacturing equipment. The optimization model is divided into two sub-items: optimization objectives and constraints. The optimization objectives are the output variables of the proxy models corresponding to the three sub-disciplines. The constraints of the geometric structure are the structural mechanical properties, the constraints of the process are the strength design requirements, and the constraints of the manufacturing equipment are the equipment capacity limit range, the manufacturing process compatibility, and the structural mechanical properties. Call the three input boxes separately through the UI, set the corresponding input box to True, and the other two input boxes to False to set the upper and lower limits of the constraints.

[0138] Users can select "Configuration", "Proxy Model", "Optimization Model", "Workflow Modification" and "Operation" in the main function area. After selecting the model in "Configuration", the system passes a zmfFilePath corresponding to the zmf model to the "Start" button. After the user sets the parameters in the parameter selection and setting area and runs it, open the bat file as a command line client, enter the command line environment that comes with the Isight model, and enter the "start file: file path" command to start the simulation of the zmf model. "Workflow Modification" can select any zmf model and open the Isight model for modification; the QProcess class is used here to start an external process. The QProcess class provides a mechanism for interacting with external programs or executing external programs and scripts. Users can modify the workflow through the QProcess class.

[0139] The result display area can display pictures and simulation results. Use Opengl to display pictures. Add an Opengl class .h and .cpp file to the project. Use Opengl's SmoothPixmapTransform to smooth the picture and improve the display quality. Use the painter.translate() function to translate the starting point of the drawing to the calculated (x, y) position to achieve the translation of the picture. When setting parameters, click the corresponding y or x item to display the corresponding picture for illustration. When clicking on the corresponding item, call textBrowser to display the simulation result Txt file to complete the design of the three main functional areas.

[0140] S52: Interface function integration. After completing the interface function design, connect the Isight model.

[0141] Connect with the Isight model through a txt text document. After setting the parameters in the parameter selection and setting area and saving them to Txt, the user clicks Run, and calls and opens the Isight model through the command line client. In the Isight model, two DataExchanger components read the parameters of Txt and pass the parameters to the system-level optimizer. After the system-level optimizer obtains the parameters, it passes them down to the subject-level optimizer, and the subject-level optimizer uses the proxy model for simulation optimization. The main function area opens the zmf model and modifies the workflow, and controls, modifies and runs the simulation process of the model through the command line client. Specifically, the connection between the front and back ends can be completed through Txt and the command line client, and the entire invention can be integrated together. The design of the integrated simulation platform for the entire composite truss structure-process-manufacturing equipment is completed.

[0142] S6: Perform composite material truss structure-process-manufacturing equipment integrated simulation according to the composite material truss structure-process-manufacturing equipment integrated simulation platform.

[0143] When conducting integrated simulation of composite truss structure-process-manufacturing equipment, the above S1 to S6 are implemented, and the multidisciplinary optimization framework of the collaborative optimization algorithm is adopted to transform the entire optimization problem into two parts: discipline-level optimization and system-level optimization. In view of the problem that the traditional simulation optimization cycle is long and some mechanism models are not yet clear, the proxy model is used to speed up the simulation speed and achieve high-precision prediction of performance indicators such as stress, strain, and strength. In view of the lack of simulation platform tools and the need to integrate third-party CAD, CAE and other software, the simulation model of this application is developed based on the Isight model. In view of the problem of model visualization, a human-computer interaction interface is developed based on the QT platform. Users can quickly modify constraints and input variables through the interface, perform simulation optimization and parameter value setting, etc., and visualize the optimized simulation scheme.

[0144] In an exemplary embodiment, Figure 2 As shown, a composite material truss structure-process-manufacturing equipment integrated simulation system is provided, which specifically includes:

[0145] The parameter acquisition module is used to obtain parameters and performance parameters corresponding to three sub-disciplines; the three sub-disciplines are truss structure, process and manufacturing equipment; the parameters include: geometric structure parameters, process parameters and manufacturing equipment parameters; the performance parameters include: structural performance, process performance and manufacturing equipment performance.

[0146] The agent model construction module is used to construct corresponding agent models based on neural networks according to the corresponding parameters of the three sub-disciplines and the corresponding performance parameters; the agent models include geometric structure agent models, process agent models and manufacturing equipment agent models; the geometric structure agent model takes geometric structure parameters as input and structural performance as output; structural performance includes: stress, strain and mode; the process agent model takes process parameters as input and process performance as output; process performance includes: product strength, straightness and surface roughness; the manufacturing equipment agent model takes manufacturing equipment parameters as input and manufacturing equipment performance as output; manufacturing equipment performance includes: size, mass and energy consumption of manufacturing equipment.

[0147] The optimization model construction module is used to construct the corresponding optimization model according to the proxy models corresponding to the three sub-disciplines and the corresponding optimization algorithm; the optimization algorithm includes: a collaborative optimization algorithm; the optimization model includes: a geometric structure optimization model, a process optimization model and a manufacturing equipment optimization model; the geometric structure optimization model takes the geometric structure parameters as input, the structural mechanical properties as constraints, and the output of the geometric structure proxy model as the optimization target; the process optimization model takes the process parameters as input, the strength design requirements as constraints, and the output of the process proxy model as the optimization target; the manufacturing equipment optimization model takes the manufacturing equipment parameters as input, the equipment capability limit range, the manufacturing process compatibility and the structural mechanical properties as constraints, and the output of the manufacturing equipment proxy model as the optimization target.

[0148] The collaborative optimization workflow construction module is used to construct a collaborative optimization workflow based on the Isight model according to the optimization model and the proxy model.

[0149] The simulation platform integration module is used to integrate based on the QT platform according to the collaborative optimization workflow to obtain an integrated simulation platform for composite material truss structure-process-manufacturing equipment.

[0150] The simulation module is used to perform composite material truss structure-process-manufacturing equipment integrated simulation based on the composite material truss structure-process-manufacturing equipment integrated simulation platform.

[0151] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store simulation platform information and process data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a composite material truss structure-process-manufacturing equipment integrated simulation method is implemented.

[0152] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0153] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0154] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0155] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A composite material truss structure-process-manufacturing equipment integrated simulation method, characterized in that: The composite material truss structure-process-manufacturing equipment integrated simulation method comprises: Obtaining parameters and performance parameters corresponding to three sub-disciplines; the three sub-disciplines are truss structure, process and manufacturing equipment; the parameters include: geometric structure parameters, process parameters and manufacturing equipment parameters; the performance parameters include: structural performance, process performance and manufacturing equipment performance; According to the corresponding parameters of the three sub-disciplines and the corresponding performance parameters, the corresponding agent models are constructed based on neural networks; the agent models include geometric structure agent model, process agent model and manufacturing equipment agent model; the geometric structure agent model takes geometric structure parameters as input and structural performance as output; structural performance includes: stress, strain and mode; the process agent model takes process parameters as input and process performance as output; process performance includes: product strength, straightness and surface roughness; the manufacturing equipment agent model takes manufacturing equipment parameters as input and manufacturing equipment performance as output; manufacturing equipment performance includes: size, mass and energy consumption of manufacturing equipment; According to the proxy models corresponding to the three sub-disciplines, corresponding optimization algorithms are used to construct corresponding optimization models; the optimization algorithms include: collaborative optimization algorithms; the optimization models include: geometric structure optimization model, process optimization model and manufacturing equipment optimization model; the geometric structure optimization model takes the geometric structure parameters as input, the structural mechanical properties as constraints, and the output of the geometric structure proxy model as the optimization target; the process optimization model takes the process parameters as input, the strength design requirements as constraints, and the output of the process proxy model as the optimization target; the manufacturing equipment optimization model takes the manufacturing equipment parameters as input, the equipment capability limit range, the manufacturing process compatibility and the structural mechanical properties as constraints, and the output of the manufacturing equipment proxy model as the optimization target; According to the optimization model and the proxy model, a collaborative optimization workflow is constructed based on an Isight model; According to the collaborative optimization workflow, integration is performed based on the QT platform to obtain an integrated simulation platform for composite truss structure-process-manufacturing equipment; According to the composite material truss structure-process-manufacturing equipment integrated simulation platform, composite material truss structure-process-manufacturing equipment integrated simulation is performed.

2. The composite material truss structure-process-manufacturing equipment integrated simulation method according to claim 1, characterized in that: The geometric structure parameters include: the total length of the truss, the cross-sectional dimensions of the truss, the thickness of the main beam and the longitudinal beam, the width of the main beam and the longitudinal beam, the pitch and pitch angle of the strip, the thickness and width of the strip; The process parameters include: pulling speed, forming pressure, heating and cooling temperature, winding parameters and main beam and longitudinal beam width; The manufacturing equipment parameters include: motor parameters, mold parameters, roller parameters, heating device parameters and main beam and longitudinal beam widths.

3. The composite material truss structure-process-manufacturing equipment integrated simulation method according to claim 1, characterized in that: The acquisition of parameters corresponding to the three sub-disciplines also includes: Construct geometry database, process database, manufacturing equipment database, equipment library and model library; The geometric structure database is used to store geometric structure parameters and corresponding structural performance; The process database is used to store process parameters and corresponding process performance; The manufacturing equipment database is used to store manufacturing equipment models and corresponding manufacturing equipment performance; The equipment warehouse is used to store motors, tensioning equipment, heating equipment, cooling equipment, winding equipment and welding equipment; The model library is used to store the geometry optimization model, the process optimization model, the manufacturing equipment optimization model, the geometry proxy model, the process proxy model, the manufacturing equipment proxy model, the neural network and the optimization algorithm.

4. The composite material truss structure-process-manufacturing equipment integrated simulation method according to claim 1, characterized in that: The step of constructing a collaborative optimization workflow based on the optimization model and the proxy model and the Isight model specifically includes: Get Task components based on the interface of the Isight model; In the Task component, a reading component is used to read parameters; the reading component includes: 2 Data Exchanger components, 2 Calculator components and 1 Optimization component; the three components are arranged from left to right, and components of the same type are parallel; In the Optimization component, the MATLAB component with added optimization algorithm is used to build and optimize the agent model.

5. The composite material truss structure-process-manufacturing equipment integrated simulation method according to claim 1, characterized in that: The interface body of the composite material truss structure-process-manufacturing equipment integrated simulation platform includes: parameter selection and setting area, main function area and result display area; The parameter selection and setting area is used to determine the parameters; The main function area is used to select functions; The result display area is used to display pictures and simulation results.

6. The composite material truss structure-process-manufacturing equipment integrated simulation method according to claim 5, characterized in that: The parameter selection and setting area is constructed using the TreeWidget control of the QT platform.

7. A composite material truss structure-process-manufacturing equipment integrated simulation system, characterized in that: The composite material truss structure-process-manufacturing equipment integrated simulation system includes: A parameter acquisition module is used to acquire parameters and performance parameters corresponding to three sub-disciplines; the three sub-disciplines are truss structure, process and manufacturing equipment; the parameters include: geometric structure parameters, process parameters and manufacturing equipment parameters; the performance parameters include: structural performance, process performance and manufacturing equipment performance; The agent model building module is used to build the corresponding agent model based on the neural network according to the corresponding parameters of the three sub-disciplines and the corresponding performance parameters; the agent model includes a geometric structure agent model, a process agent model and a manufacturing equipment agent model; the geometric structure agent model takes the geometric structure parameters as input and the structural performance as output; the structural performance includes: stress, strain and mode; the process agent model takes the process parameters as input and the process performance as output; the process performance includes: the strength, straightness and surface roughness of the product; the manufacturing equipment agent model takes the manufacturing equipment parameters as input and the manufacturing equipment performance as output; the manufacturing equipment performance includes: the size, mass and energy consumption of the manufacturing equipment; The optimization model construction module is used to construct the corresponding optimization model according to the proxy models corresponding to the three sub-disciplines by using the corresponding optimization algorithms; the optimization algorithms include: collaborative optimization algorithm; the optimization models include: geometric structure optimization model, process optimization model and manufacturing equipment optimization model; the geometric structure optimization model takes the geometric structure parameters as input, the structural mechanical properties as constraints, and the output of the geometric structure proxy model as the optimization target; the process optimization model takes the process parameters as input, the strength design requirements as constraints, and the output of the process proxy model as the optimization target; the manufacturing equipment optimization model takes the manufacturing equipment parameters as input, the equipment capability limit range, the manufacturing process compatibility and the structural mechanical properties as constraints, and the output of the manufacturing equipment proxy model as the optimization target; A collaborative optimization workflow construction module, used to construct a collaborative optimization workflow based on the Isight model according to the optimization model and the proxy model; A simulation platform integration module, which is used to integrate the collaborative optimization workflow based on the QT platform to obtain an integrated simulation platform for composite truss structure-process-manufacturing equipment; The simulation module is used to perform composite material truss structure-process-manufacturing equipment integrated simulation based on the composite material truss structure-process-manufacturing equipment integrated simulation platform.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the composite material truss structure-process-manufacturing equipment integrated simulation method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the composite material truss structure-process-manufacturing equipment integrated simulation method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the composite material truss structure-process-manufacturing equipment integrated simulation method described in any one of claims 1 to 6 is implemented.

Images