CN115544842A - Welding deformation simulation method, device, equipment and storage medium - Google Patents
Welding deformation simulation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115544842A CN115544842A CN202211260512.2A CN202211260512A CN115544842A CN 115544842 A CN115544842 A CN 115544842A CN 202211260512 A CN202211260512 A CN 202211260512A CN 115544842 A CN115544842 A CN 115544842A
- Authority
- CN
- China
- Prior art keywords
- welding
- finite element
- model
- deformation
- temperature field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000003466 welding Methods 0.000 title claims abstract description 163
- 238000000034 method Methods 0.000 title claims abstract description 99
- 238000004088 simulation Methods 0.000 title claims abstract description 30
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000009826 distribution Methods 0.000 claims abstract description 91
- 230000008569 process Effects 0.000 claims abstract description 58
- 238000003062 neural network model Methods 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 28
- 238000000605 extraction Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 13
- 210000001503 joint Anatomy 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000013075 data extraction Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010252 digital analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Numerical Control (AREA)
Abstract
The embodiment of the invention provides a method, a device, equipment and a storage medium for simulating welding deformation, and relates to the field of welding simulation. The simulation method comprises S1, obtaining a first finite element model of a welding joint to be simulated, and carrying out a welding process. And S2, calculating and extracting target temperature field distribution data through a temperature field finite element analysis method according to the welding process and the first finite element model. And S3, inputting the target temperature field distribution data into a pre-trained BP neural network model to obtain the residual plastic strain distribution. And S4, updating the first finite element model by taking the residual plastic strain distribution as the inherent strain distribution. And S5, calculating to obtain the integral deformation of the welding joint through an elastic finite element analysis method according to the updated first finite element model. The process of obtaining the welding residual plastic strain through the long-time thermal-elastic-plastic finite element stress iterative calculation is avoided by replacing the finite element iterative calculation process with the BP neural network prediction, and the high efficiency of the deformation prediction is realized.
Description
Technical Field
The invention relates to the technical field of welding simulation, in particular to a welding deformation simulation method, device, equipment and storage medium.
Background
Welding is a very important and critical area in manufacturing. Efficient prediction of the deformation of welded structures has been one of the key problems of the welding discipline.
Although a deformation calculation method such as a thermo-elastic-plastic finite element method has been developed, the conventional finite element analysis method has a large calculation amount and a low simulation efficiency, thereby affecting the production efficiency.
The efficient prediction of the welding deformation has important influences on the aspects of guiding the optimization of the welding process, providing theoretical guidance for the deformation control of actual welding product manufacturing, reducing the welding production time, material cost and the like, and a key technology for efficiently predicting the welding structure deformation considering both the prediction efficiency and the prediction precision is urgently needed to be developed.
In view of the above, the applicant has specifically proposed the present application after studying the existing technologies.
Disclosure of Invention
The present invention provides a method, apparatus, device and storage medium for simulating welding deformation to improve at least one of the above technical problems.
First aspect,
The embodiment of the invention provides a welding deformation simulation method which comprises a step S1 to a step S5.
S1, obtaining a first finite element model of a welding joint to be simulated, and carrying out a welding process.
And S2, calculating and extracting target temperature field distribution data through a temperature field finite element analysis method according to the welding process and the first finite element model.
And S3, inputting the target temperature field distribution data into a pre-trained BP neural network model to obtain the residual plastic strain distribution.
And S4, updating the first finite element model by taking the residual plastic strain distribution as the inherent strain distribution.
And S5, calculating to obtain the integral deformation of the welding joint through an elastic finite element analysis method according to the updated first finite element model.
The second aspect,
The embodiment of the invention provides a welding deformation simulation device, which comprises:
and the initial data acquisition module is used for acquiring a first finite element model of the welding joint to be simulated and a welding process.
And the temperature field calculation module is used for calculating and extracting target temperature field distribution data through a temperature field finite element analysis method according to the welding process and the first finite element model.
And the plastic strain acquisition module is used for inputting the target temperature field distribution data into a pre-trained BP neural network model to acquire residual plastic strain distribution.
And the model updating module is used for updating the first finite element model by taking the residual plastic strain distribution as the inherent strain distribution.
And the deformation calculation module is used for calculating the integral deformation of the welding joint according to the updated first finite element model by an elastic finite element analysis method.
The third aspect,
The embodiment of the invention provides a welding deformation simulation device which comprises a processor, a memory and a computer program stored in the memory. A computer program is executable by a processor to implement the method of simulating a weld deformation as described in any of the paragraphs above.
The fourth aspect,
An embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the apparatus on which the computer-readable storage medium is located is controlled to execute the method for simulating welding deformation according to any one of the paragraphs above.
By adopting the technical scheme, the invention can obtain the following technical effects:
according to the embodiment of the invention, the process of finite element iterative computation is replaced by BP neural network prediction, so that the process of obtaining welding residual plastic strain by long-time thermal-elastic-plastic finite element stress iterative computation is avoided, the whole prediction process is completed within tens of minutes, and the high efficiency of deformation prediction is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow diagram of a simulation method.
FIG. 2 is a schematic representation of extracted temperature field distribution data and residual plastic strain distribution data.
Fig. 3 is a schematic diagram of a model coordinate system.
FIG. 4 is a schematic diagram of a BP neural network model structure.
Fig. 5 is an error distribution diagram of the predicted values of the simulation method.
FIG. 6 is a schematic view of a flat joint deformation measurement line.
FIG. 7 is a graph comparing the results of deformation calculations by the simulation method and the thermo-elastic-plastic finite element method.
Fig. 8 is a schematic structural diagram of the simulation apparatus.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment,
Referring to fig. 1 to 6, a first embodiment of the present invention provides a welding deformation simulation method, which can be performed by a welding deformation simulation apparatus (hereinafter referred to as simulation apparatus). In particular, execution by one or more processors in the simulation device to implement steps S1-S5.
S1, obtaining a first finite element model of a welding joint to be simulated, and carrying out a welding process. Preferably, the first finite element model is of the type: the flat plate butt joint is of a first-order tetrahedral unit type.
Specifically, a welded joint refers to a joint where two or more parts are to be joined by welding. Or a joint where two or more parts are joined by a welding process, including a weld, a fusion zone, and a heat affected zone. The joint types of the welding joint suitable for the simulation method of the present invention include, but are not limited to: butt weld joints, T-joints, angle joints, and lap joints.
Preferably, the welding process includes, but is not limited to: process type, welding power and welding speed. The simulation method of the present invention is applicable to process types including, but not limited to: an arc welding process and a high energy beam welding process.
In this embodiment, the simulation device may be an electronic device with computing capability, such as a portable notebook computer, a desktop computer, a server, a smart phone, or a tablet computer. Specifically, inteweld is used as the welding simulation software. Inteweld is a welding structure stress deformation process simulation software. The welding simulation software realizes the packaging of mathematical and process modeling operations on the welding physical problem, and the solver of the welding simulation software realizes the solution of the final deformation of the invention.
And S2, calculating and extracting target temperature field distribution data through a temperature field finite element analysis method according to the welding process and the first finite element model. On the basis of the foregoing embodiment, in an optional embodiment of the present invention, step S2 specifically includes step S21 to step S22.
S21, calculating a temperature field of the first finite element model through a temperature field finite element analysis method according to the welding process and the first finite element model;
and S22, extracting target temperature field distribution data of the target area according to the temperature field. Wherein the target region is a middle section extraction region (i.e., an extraction region near a weld) of the weld joint. Specifically, the method comprises the following steps:
the weld joint middle section is defined as: a point strain dialog box of a welding deformation prediction module based on the secondary development of Inteweld software extracts a central point coordinate through setting data, sets the length direction V and the length size, and sets a rectangular section area obtained by the width direction W and the width size. The sizes in the length direction and the width direction are manually performed according to actual needs, and the invention is not particularly limited to this.
The target temperature field distribution data is defined as: and setting total n multiplied by m point data obtained by a horizontal point number n and a longitudinal point number m by using a point strain dialog box of a welding deformation prediction module based on the secondary development of Inteweld software according to the set middle section extraction area.
And S3, inputting the target temperature field distribution data into a pre-trained BP neural network model to obtain the residual plastic strain distribution.
According to the embodiment of the invention, the BP neural network prediction is used for replacing the finite element iterative computation process, so that the inherent strain distribution is rapidly obtained, and a new thought is provided for the efficient prediction of the deformation of the welding joint structure. The process of obtaining the welding residual plastic strain through long-time thermal elastic plastic finite element stress iterative calculation is avoided, the whole prediction process is completed within tens of minutes, and the high efficiency of deformation prediction is realized.
Specifically, a preprocessing program for integrating corresponding neural network training data is compiled by adopting a C + + language, a BP neural network prediction model frame is compiled by adopting MATLAB software, a Qt frame is adopted, and a temperature field and residual plastic strain data extraction and derivation interactive interface is compiled by relying on InteWeld software, so that researches and technologists are supported to carry out final welding deformation calculation through software interface operation modeling and applying the method, and an important means is provided for welding structure design and process parameter optimization.
And S4, updating the first finite element model by taking the residual plastic strain distribution as the inherent strain distribution. Specifically, the welding simulation software used in the embodiment of the present invention is InteWeld software. Preferably, step S4 specifically includes steps S41 to S42.
And S41, converting the residual plastic strain distribution into a join file supported by an InteWeld software structural part module.
S42, a joint file is loaded by designating a welding line sign line in the Inteweld software, so that the inherent strain distribution is loaded to the whole welding direction of the welding joint, and the first finite element model is updated.
Specifically, according to the theoretical basis of the inherent strain, the distribution of the residual plastic strain is approximate to the distribution of the inherent strain, and the residual plastic strain is uniformly distributed along the direction of the welding seam and basically consistent in size. Wherein, in the total strain component of the welded joint structure: the far components of transformation strain, creep strain and thermal strain are smaller than the residual plastic strain components.
Therefore, in the present embodiment, the residual plastic strain distribution is obtained as the inherent strain distribution by prediction and is converted into a join file supported by the intewedd software structure module. Then setting the width of the loading region as the middle section temperature and the width of the strain distribution extraction region (namely: the target region/the middle section extraction region), finally appointing a 'welding seam mark line' in the Inteweld software to load the inherent strain distribution, and loading the predicted inherent strain distribution to the whole welding seam direction of the welding joint structure.
And S5, calculating to obtain the integral deformation of the welding joint through an elastic finite element analysis method according to the updated first finite element model.
Specifically, the load inherent strain is used as an initial strain, and the overall deformation is calculated by an elastic finite element method. And the deformation calculation is completed through the deformation solving of a structural part module of Inteweld software.
It can be understood that the intelligent and digital technology is more and more widely applied to welding manufacturing production, and the quality of a welding product can be effectively ensured by obtaining information in the welding process to achieve the purpose of predicting a final welding result. However, the mainstream welding deformation digital analysis method still has respective limitations, and the high-efficiency prediction of the welding structure deformation is difficult to realize.
According to the embodiment of the invention, through the ideas of simulating human cognitive welding process information and transfer learning, the welding temperature field distribution is extracted, a neural network model is established, then the welding residual plastic strain distribution is rapidly predicted through the model, then the final deformation is calculated by combining the residual plastic strain distribution meeting the precision requirement, namely the inherent strain distribution with the inherent strain theory, the prediction error precision meets the digital simulation requirement of the design and manufacture of actual advanced welding parts, and the problem that the prediction precision and the efficiency of the welding structure deformation are difficult to take into account is solved.
According to the embodiment of the invention, the process of finite element iterative computation is replaced by BP neural network prediction, so that the process of obtaining welding residual plastic strain by long-time thermal-elastic-plastic finite element stress iterative computation is avoided, the whole prediction process is completed within tens of minutes, and the high efficiency of deformation prediction is realized.
On the basis of the above embodiments, in an optional embodiment of the present invention, the training step of the BP neural network model includes steps A1 to A4.
A1, establishing a second finite element model of the welding joint for training, and acquiring a plurality of welding process groups.
And A2, combining the second finite element models according to a plurality of welding processes, and respectively calculating a plurality of temperature fields and stress fields of the welding joint for training by a thermal-elastic-plastic finite element analysis method.
Specifically, the thermal-elastic-plastic finite element analysis of the welding joint is carried out by adopting Inteweld software, the obtained welding temperature field distribution data and the residual plastic strain data are stored in a file with the suffix of ". Plt",
and A3, constructing a model coordinate system according to the second finite element model, and extracting temperature field distribution data and residual plastic strain distribution data of the target region from the plurality of temperature fields and stress fields respectively according to the model coordinate system.
Specifically, a schematic diagram of temperature distribution and residual plastic strain distribution data extraction of the target region is shown in fig. 2.
The target region is a middle section extraction region of the weld joint (i.e., an extraction region near the weld). The weld joint middle section is defined as: a point strain dialog box of a welding deformation prediction module based on the secondary development of Inteweld software extracts a central point coordinate through setting data, sets the length direction V and the length size, and sets a rectangular section area obtained by the width direction W and the width size. The sizes in the length direction and the width direction are manually performed according to actual needs, and the invention is not particularly limited to this.
The target temperature field distribution data and the residual plastic strain distribution data are defined as: and setting total n multiplied by m point data obtained by a horizontal point number n and a longitudinal point number m by using a point strain dialog box of a welding deformation prediction module based on the secondary development of Inteweld software according to the set middle section extraction area.
On the basis of the foregoing embodiment, in an optional embodiment of the present invention, step A3 specifically includes step a31 to step a33:
and A31, determining a third axis by using a right-hand spiral rule by using a welding seam sign line and a welding gun direction perpendicular to the welding seam sign line as two axes according to the second finite element model by using the welding seam middle point as an original point so as to construct a model coordinate system. Wherein the model coordinate system is a Cartesian coordinate system.
Specifically, a weld marking line and a welding gun direction are selected from intewedd software, and a joint weld coordinate system is established, as shown in fig. 3.
And A32, acquiring a section extraction area (shown in figure 2) consisting of the center point coordinate of the welding seam, and n points in the transverse direction and m points in the longitudinal direction of the gravity center point coordinate according to the model coordinate system.
And A33, extracting temperature field distribution data and residual plastic strain distribution data from the plurality of temperature fields and stress fields respectively according to the section extraction region.
And A4, training and obtaining a BP neural network model by taking the temperature field distribution data as input and the residual plastic strain distribution data as output.
Specifically, the BP neural network model structure is established according to a neural network tool kit provided by MATLAB software. Before the establishment, setting: the number of nodes of the input layer, the hidden layer and the output layer, the activation function from the input layer to the hidden layer, the activation function from the hidden layer to the output layer, the maximum times of training iteration, the learning rate, the target precision and necessary parameters including the training function. It can be understood that the construction of the neural network model is a conventional technical means of those skilled in the art, and the present invention does not specifically limit parameters such as the number of nodes, the activation function, and the number of training iterations, and the like of the model, and belongs to the protection scope of the present invention as long as the model belongs to the BP neural network model.
In this embodiment, establishing the BP neural network model includes two steps of acquiring training data and training a model.
The acquiring of the training data specifically includes: and B01, establishing a finite element mesh model of the welding joint (as shown in figure 4). And B02, setting a plurality of process groups with two factors of welding power and welding speed changing for neural network training. And B03, calculating the temperature field and the stress field of the welded joint by adopting a thermal-elastic-plastic finite element according to a plurality of groups of process groups and a finite element grid model. And B04, establishing a welding joint model coordinate system, wherein the coordinate system takes the middle point of the model welding seam as an original point, takes the welding path and the welding gun direction perpendicular to the welding path as two axes, and determines a third axis according to a right-hand screw rule to obtain an established Cartesian coordinate system. Wherein the weld joint model coordinate system is defined as: and determining a third axis by using a right-hand spiral rule by using the middle point of the welding line as an original point and the welding line sign line and the direction of the welding gun vertical to the welding line sign line as two axes to establish a Cartesian coordinate system. And B05, extracting temperature field distribution data and residual plastic strain distribution data near the welding seam of the middle section of the welding joint from the temperature field and the stress field according to the welding joint model coordinate system.
The training model specifically comprises: and B06, establishing a BP neural network model, wherein the model takes the extracted temperature field distribution data as input and takes the residual plastic strain distribution data as output.
It can be understood that after the BP neural network model is constructed, it needs to be verified to ensure the accuracy of its simulation. Specifically, the specific parameters of the four sets of target process sets for detecting the accuracy of the prediction of the residual plastic strain distribution of the BP neural network are shown in table 1.
TABLE 1 welding Process parameters to validate BP neural network model
| Serial number | Laser power (W) | Welding speed (mm/s) |
| 1 | 1400 | 13 |
| 2 | 1800 | 18 |
| 3 | 2000 | 21 |
| 4 | 2200 | 25 |
Under the four sets of process parameters shown in table 1, the distribution of absolute percentage errors between the simulated values and the predicted values of equivalent plastic residual strain in the Y direction and Z direction coordinate values of all data points in the YZ section intercept area shown in fig. 2 is used, as shown in fig. 5. The comparison of the deformation calculation result and the actual deformation measurement result by the hot elastic-plastic finite element method under the four groups of process parameters shown in the table 1 by using the method of the invention is shown in fig. 7. The deformation measurement lines of the plate joint set for quantitative comparison of the deformation prediction results are shown as lines AB, CD and EF in FIG. 6.
The second aspect,
The embodiment of the invention provides a welding deformation simulation device, which comprises:
the initial data acquisition module 1 is used for acquiring a first finite element model of a welding joint to be simulated and a welding process.
And the temperature field calculation module 2 is used for calculating and extracting target temperature field distribution data through a temperature field finite element analysis method according to the welding process and the first finite element model.
And the plastic strain acquisition module 3 is used for inputting the target temperature field distribution data into a pre-trained BP neural network model to acquire residual plastic strain distribution.
And the model updating module 4 is used for updating the first finite element model by taking the residual plastic strain distribution as the inherent strain distribution.
And the deformation calculation module 5 is used for calculating the integral deformation of the welding joint according to the updated first finite element model by an elastic finite element analysis method.
On the basis of the above embodiment, in an alternative embodiment of the present invention, the welding simulation software used in the present invention is InteWeld software. The model updating module 4 specifically includes:
and the file conversion unit is used for converting the residual plastic strain distribution into a join file supported by the InteWeld software structural component module.
And the file loading unit is used for appointing a welding seam mark line in the Inteweld software to load a join file, so that the inherent strain distribution is loaded to the whole welding seam direction of the welding joint, and the first finite element model is updated.
On the basis of the above embodiments, in an optional embodiment of the present invention, the welding deformation simulation apparatus further includes a training module of a BP neural network model. The training module comprises:
and the training data acquisition unit is used for establishing a second finite element model of the welding joint for training and acquiring a plurality of welding process groups.
And the training data simulation unit is used for combining the second finite element models according to a plurality of welding processes and respectively calculating a plurality of temperature fields and stress fields of the welding joint for training by a thermal-elastic-plastic finite element analysis method.
And the training data extraction unit is used for constructing a model coordinate system according to the second finite element model and extracting temperature field distribution data and residual plastic strain distribution data from the plurality of temperature fields and stress fields respectively according to the model coordinate system.
And the model training unit is used for training and obtaining the BP neural network model by taking the temperature field distribution data as input and the residual plastic strain distribution data as output.
On the basis of the foregoing embodiment, in an optional embodiment of the present invention, the training data extracting unit specifically includes:
and the coordinate system constructing subunit is used for determining a third axis by using a right-hand spiral rule by taking the middle point of the welding seam as an original point and the welding seam sign line and the welding gun direction perpendicular to the welding seam sign line as two axes according to the second finite element model so as to construct a model coordinate system. Wherein the model coordinate system is a Cartesian coordinate system.
And the extraction region construction subunit is used for acquiring the center point coordinate of the welding seam and a section extraction region consisting of n points in the transverse direction and m points in the longitudinal direction of the gravity center point coordinate according to the model coordinate system.
And the training data extraction subunit is used for extracting temperature field distribution data and residual plastic strain distribution data from the plurality of temperature fields and stress fields respectively according to the section extraction area.
Example III,
The embodiment of the invention provides a welding deformation simulation device which comprises a processor, a memory and a computer program stored in the memory. The computer program can be executed by a processor to implement the method of simulating a weld deformation as described in any of the paragraphs above.
Examples IV,
An embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, an apparatus on which the computer-readable storage medium is located is controlled to perform the method for simulating welding deformation according to any one of the paragraphs of the embodiment.
In the embodiments provided in the embodiments of the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus and method embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship.
The word "if" as used herein may be interpreted as "at 8230; \8230;" or "when 8230; \8230;" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (a stated condition or event)" may be interpreted as "upon determining" or "in response to determining" or "upon detecting (a stated condition or event)" or "in response to detecting (a stated condition or event)", depending on the context.
In the embodiments, the references to "first \ second" are merely to distinguish similar objects and do not represent a specific ordering for the objects, and it is to be understood that "first \ second" may be interchanged with a specific order or sequence, where permitted. It should be understood that "first \ second" distinct objects may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced in sequences other than those illustrated or described herein.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A method of simulating weld deformation, comprising:
acquiring a first finite element model of a welding joint to be simulated and a welding process;
calculating and extracting target temperature field distribution data by a temperature field finite element analysis method according to the welding process and the first finite element model;
inputting the target temperature field distribution data into a pre-trained BP neural network model to obtain residual plastic strain distribution;
updating the first finite element model by taking the residual plastic strain distribution as an inherent strain distribution;
and calculating the integral deformation of the welding joint by an elastic finite element analysis method according to the updated first finite element model.
2. The method of simulating welding deformation of claim 1, wherein the training step of the BP neural network model comprises:
establishing a second finite element model of the welding joint for training, and acquiring a plurality of welding process groups;
combining the second finite element model according to the plurality of welding processes, and respectively calculating a plurality of temperature fields and stress fields of the welding joint for training by a thermal-elastic-plastic finite element analysis method;
constructing a model coordinate system according to the second finite element model, and extracting temperature field distribution data and residual plastic strain distribution data from a plurality of temperature fields and stress fields respectively according to the model coordinate system;
and training and obtaining the BP neural network model by taking the temperature field distribution data as input and the residual plastic strain distribution data as output.
3. The method for simulating welding deformation according to claim 2, wherein a model coordinate system is constructed according to the second finite element model, and the temperature field distribution data and the residual plastic strain distribution data are extracted from a plurality of temperature fields and stress fields respectively according to the model coordinate system, and the method specifically comprises the following steps:
according to the second finite element model, a third axis is determined by using a right-hand spiral rule by taking a middle point of a welding seam as an original point and taking a welding seam sign line and a welding gun direction perpendicular to the welding seam sign line as two axes so as to construct a model coordinate system; wherein the model coordinate system is a Cartesian coordinate system;
according to the model coordinate system, obtaining the center point coordinate of the welding seam, and a section extraction area consisting of n points in the transverse direction and m points in the longitudinal direction of the gravity center point coordinate;
and extracting temperature field distribution data and residual plastic strain distribution data from a plurality of temperature fields and stress fields respectively according to the section extraction region.
4. The method for simulating welding deformation according to claim 1, wherein the welding simulation software used in the present invention is InteWeld software.
5. The method for simulating welding deformation according to claim 4, wherein updating the first finite element model with the residual plastic strain distribution as an inherent strain distribution specifically comprises:
converting the residual plastic strain distribution into a join file supported by an InteWeld software structural part module;
and (3) specifying a weld mark line loading join file in the Inteweld software so as to load the inherent strain distribution to the whole weld direction of the welding joint to update the first finite element model.
6. The simulation method of welding deformation according to any one of claims 1 to 5, wherein the joint types of the welding joint include a butt joint, a T-joint, a fillet joint, and a lap joint;
the welding process comprises a process type, welding power and welding speed;
the process types include arc welding processes and high energy beam welding processes.
7. A welding deformation simulation apparatus, comprising:
the initial data acquisition module is used for acquiring a first finite element model of a welding joint to be simulated and a welding process;
the temperature field calculation module is used for calculating and extracting target temperature field distribution data through a temperature field finite element analysis method according to the welding process and the first finite element model;
the plastic strain acquisition module is used for inputting the target temperature field distribution data into a pre-trained BP neural network model to acquire residual plastic strain distribution;
the model updating module is used for updating the first finite element model by taking the residual plastic strain distribution as an inherent strain distribution;
and the deformation calculation module is used for calculating the integral deformation of the welding joint according to the updated first finite element model by an elastic finite element analysis method.
8. A welding deformation simulation apparatus comprising a processor, a memory, and a computer program stored in the memory; the computer program is executable by the processor to implement a method of simulating a weld deformation according to any one of claims 1 to 6.
9. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the method of simulating a welding deformation according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211260512.2A CN115544842A (en) | 2022-10-14 | 2022-10-14 | Welding deformation simulation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211260512.2A CN115544842A (en) | 2022-10-14 | 2022-10-14 | Welding deformation simulation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115544842A true CN115544842A (en) | 2022-12-30 |
Family
ID=84735340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211260512.2A Withdrawn CN115544842A (en) | 2022-10-14 | 2022-10-14 | Welding deformation simulation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115544842A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116663354A (en) * | 2023-05-12 | 2023-08-29 | 中国建筑第二工程局有限公司 | Sheet deformation calculation method, apparatus, device, and storage medium |
| CN117688802A (en) * | 2023-11-28 | 2024-03-12 | 广东工业大学 | Method and device for calculating deformation compensation of crude oil-to-barge stern subsection manufacturing |
-
2022
- 2022-10-14 CN CN202211260512.2A patent/CN115544842A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116663354A (en) * | 2023-05-12 | 2023-08-29 | 中国建筑第二工程局有限公司 | Sheet deformation calculation method, apparatus, device, and storage medium |
| CN116663354B (en) * | 2023-05-12 | 2024-01-30 | 中国建筑第二工程局有限公司 | Sheet deformation calculation method, apparatus, device, and storage medium |
| CN117688802A (en) * | 2023-11-28 | 2024-03-12 | 广东工业大学 | Method and device for calculating deformation compensation of crude oil-to-barge stern subsection manufacturing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115544842A (en) | Welding deformation simulation method, device, equipment and storage medium | |
| Zhang et al. | Kinematic reliability analysis of robotic manipulator | |
| Lindau et al. | Efficient contact modeling in nonrigid variation simulation | |
| Promyoo et al. | Innovative digital manufacturing curriculum for industry 4.0 | |
| CN102152016A (en) | Method for simulation of welding distortion | |
| US20210027003A1 (en) | Method and device for modelling and fatigue strength assessment of weld seams between mechanical parts | |
| Ilgin et al. | Simultaneous determination of disassembly sequence and disassembly-to-order decisions using simulation optimization | |
| Du et al. | Optimal design of fixture layout for compliant part with application in ship curved panel assembly | |
| Bae et al. | Estimating effect of additional sample on uncertainty reduction in reliability analysis using Gaussian process | |
| Do Koo et al. | Estimation of residual stress in welding of dissimilar metals at nuclear power plants using cascaded support vector regression | |
| Leifsson et al. | Aerodynamic design optimization: physics-based surrogate approaches for airfoil and wing design | |
| Na et al. | Residual stress prediction of dissimilar metals welding at NPPs using support vector regression | |
| Zhong et al. | Differential correction and arc-length continuation applied to boundary value problems: Examples based on snap-through of circular arches | |
| Mai et al. | A robust physics-informed neural network approach for predicting structural instability | |
| Shibahara et al. | Approach to automation of line heating by combination of reinforcement learning and finite element method simulation | |
| Belitzki et al. | Distortion minimization of laser beam welded components by the use of finite element simulation and artificial intelligence | |
| CN107491841A (en) | Nonlinear optimization method and storage medium | |
| Ni et al. | A mechanism informed neural network for predicting machining deformation of annular parts | |
| Ram et al. | Stochastic design exploration with rework of flexible manufacturing system under copula-coverage approach | |
| Villarreal-Marroquin et al. | A sequential surrogate-based multiobjective optimization method: effect of initial data set | |
| Kling et al. | A hybrid subspace analysis procedure for non-linear postbuckling calculation | |
| Bai et al. | Hybrid inversion method and sensitivity analysis of inherent deformations of welded joints | |
| Zhao et al. | Prediction of assembly variation during early design | |
| Aktaa et al. | Non-linear failure analysis of HCPB Test Blanket Module | |
| Zhang et al. | A Dendrite Net based decoupled framework for the reliability‐based control co‐design problem |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221230 |
|
| WW01 | Invention patent application withdrawn after publication |