CN114662232A - Forming quality analysis method for hot stamping part with complex shape - Google Patents
Forming quality analysis method for hot stamping part with complex shape Download PDFInfo
- Publication number
- CN114662232A CN114662232A CN202210243169.4A CN202210243169A CN114662232A CN 114662232 A CN114662232 A CN 114662232A CN 202210243169 A CN202210243169 A CN 202210243169A CN 114662232 A CN114662232 A CN 114662232A
- Authority
- CN
- China
- Prior art keywords
- slice
- feature
- database
- combination
- information
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/22—Moulding
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Linguistics (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a forming quality analysis method of a hot stamping part with a complex shape, which comprises the steps of establishing a three-dimensional model; extracting position information of all points and coordinate information comprising three coordinate axis directions of x, y and z, and establishing a three-dimensional point set information database; dividing section slices of the part, and constructing a slice combination database; sequentially extracting coordinate information of the slice combination to construct a slice coordinate information database; correlating the relationship between the feature information and the position information of the single slice; constructing a slice characteristic database; judging whether the slice coordinate information database is traversed or not; performing machine self-learning, and forming a feature recognition evaluation model; establishing a database for the characteristic data conforming to the characteristic identification and evaluation model; and judging whether the slice combination database is traversed, and dividing the original hot stamping part with the complex shape into a combination of stamping parts with basic shapes and outputting the combination. The system relates the geometric characteristics of the hot stamping part with the complex shape with the stamping forming process parameters, and improves the parameter optimization efficiency.
Description
Technical Field
The invention relates to the technical field of metal plastic forming, in particular to a forming quality analysis method of a hot stamping part with a complex shape.
Background
The design of the hot stamping forming process based on the traditional method generally comprises the following process qualitative analysis, physical simulation test, actual production verification and the like, related process design mainly depends on the design experience of workers, and after the hot stamping forming die is initially designed and trial-manufactured, the design parameters, the process parameters and the like are repeatedly finished through a trial-and-error method to finally complete the whole design. In actual production, parts formed by hot stamping are complex in shape and complex in outline size, deformation states of all parts of a blank are complex when the parts are formed, stress distribution is uneven, the parts are prone to wrinkling, cracking and other defects in the forming process, and direct process design is very difficult.
The existing simulation analysis technology for hot stamping forming of parts is to establish a three-dimensional model of the part, then establish a three-dimensional model of a simplified die, perform grid division in CAE software, input relevant stamping process parameters to perform simulation analysis, obtain a forming quality result of the stamped part, and can effectively save design time and reduce die design cost.
Due to market demands, the geometric shapes of punched finished products, such as automobile fenders, automobile A pillars and the like, are more and more complex, and how to ensure the mechanical property requirements of parts after punching and forming also puts requirements on the improvement of the punching process. In the stamping process of the metal plate, the material undergoes elastic-plastic deformation, and the relationship between the stamping forming process parameters and the forming quality is often highly nonlinear, so that the method is very critical for finding the nonlinear relationship between the plate forming process parameters and the forming quality and carrying out control optimization on a plurality of forming defects. If a conventional analysis method is adopted, the requirement on a computer is particularly high, the speed of the simulation analysis process cannot meet the production requirement, and the forming quality and precision of the simulated parts are poor.
Disclosure of Invention
In view of the above, the present invention is directed to a method for analyzing forming quality of a hot-stamped part with a complex shape, which can solve the above technical problems.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a forming quality analysis method of a hot-stamped part with a complex shape comprises the following steps:
step 1: establishing a three-dimensional model of a hot stamping part with a complex shape;
step 2: extracting position information of all points of the hot stamping part with the complex shape and coordinate information comprising three coordinate axis directions of x, y and z, and establishing a three-dimensional point set information database;
and step 3: dividing part section slices according to position information of all points of the hot stamping part with the complex shape, extracting three adjacent part section slices to form a slice combination, and constructing a slice combination database;
and 4, step 4: sequentially extracting coordinate information of the slice combination to perform traversal operation;
and 5: constructing a slice coordinate information database;
step 6: correlating the relation between the characteristic information and the position information of the single slice and performing traversal operation;
and 7: constructing a slice characteristic database and storing the associated slice characteristic information and position information data;
and 8: judging whether the traversal of the slice coordinate information database is completed or not, and if so, entering a step 9; if the traversal is not completed, returning to the step 6;
and step 9: utilizing the data of the characteristic database to carry out machine self-learning and form a characteristic identification evaluation model;
step 10: judging whether each feature data of the feature database conforms to the feature identification evaluation model, and if so, entering the step 11; if the data do not meet the requirement, inputting the characteristic data into a step 9 for machine self-learning;
step 11: establishing a feature recognition model database for feature data conforming to the feature recognition evaluation model;
step 12: judging whether the traversal of the slice combination database is completed or not, and entering a step 13 if the traversal is completed; if not, returning to the step 4;
step 13: performing characteristic evaluation and integration on the characteristic identification model;
step 14: dividing the original hot stamping part with the complex shape into a combination of stamping parts with basic shapes;
step 15: and outputting the combination of the basic shape stamping parts and carrying out subsequent finite element simulation analysis.
Further, in the step 3, the method of dividing the section slices of the part according to the position information of all points of the hot-stamped part with the complex shape and extracting the section slices of three adjacent parts to form the slice combination includes selecting one coordinate axis direction of x, y and z as the section direction, selecting a set of three-dimensional points corresponding to each coordinate value on the coordinate axis as one section slice, selecting three adjacent section slices with equal intervals along the section direction as one slice combination, wherein the section slices in the slice combination are marked as the ith slice, the (i + 1) th slice and the (i + 2) th slice, and i is an integer greater than or equal to 1.
Further, the relation method for associating the feature information and the position information of the single slice in step 6 is to extract three continuous feature coordinates in each single slice according to the position sequence, identify a connecting feature of three coordinate points as a line segment or an arc as the feature information, extract the position information of the three continuous feature coordinates, and associate the feature information with the position information.
Further, in the step 9, the specific method for performing machine self-learning by using the data of the feature database and forming the feature recognition evaluation model is to select a specific amount of feature information from the feature database to construct a data set with geometric features of the basic stamping part, perform feature recognition training by using a feature recognition algorithm of machine learning, and form the feature recognition evaluation model.
Further, the geometric features for constructing the data set with the geometric features of the basic stamping part comprise line segment features and circular arc features.
Further, a specific method for performing feature recognition training by using a feature recognition algorithm of machine learning and forming a feature recognition evaluation model is that in each slice combination, in the same slice, line segments or arcs are subjected to associated recognition, and line segments or arcs with the same features are spliced into line segments or arcs with larger scales; and performing correlation identification on line segments or circular arc characteristics between every two adjacent slices, and splicing the line segments or circular arcs with the same characteristics into a plane or a circular arc surface.
Further, the method for determining whether the feature data conforms to the feature recognition evaluation model in step 10 is to regard the features having the same features as positive examples and those not having the same features as negative examples, and evaluate the features by using a formula
Wherein:
TP (true Positive): indicating the number of times that the judgment is positive and correct;
FP (false Positive) indicates the number of times of judgment errors when judging as a positive example;
tn (true negative): the number of times of judging as negative example and judging as correct is shown;
FN (false negative) indicates the number of times of determination errors when a negative case is determined.
Further, the method for evaluating and integrating the features of the feature recognition model in step 13 is to splice the same features in the current slice combination and the adjacent slice combination in the feature recognition model database, compare the spliced features with the set error, if the spliced features are within the set error range, the spliced features are retained, and if the spliced features are outside the set error range, the slice combination adjacent to the current slice combination is removed.
According to the forming quality analysis method for the hot stamping part with the complex shape, the geometric characteristics are extracted, the characteristic identification is carried out on the hot stamping part with the complex shape, the geometric characteristics of the hot stamping part with the complex shape are connected with the stamping forming process parameters, the parameter optimization efficiency is improved, a mathematical model with a simple relative structure can be found to approximate the nonlinear relation between the forming parameters and the forming quality target function, the sheet stamping simulation times can be reduced, the optimized parameters can be quickly obtained, the simulation efficiency is improved, the forming defects are effectively controlled, the forming quality is improved, and the method has important significance for the design of the hot stamping forming process of the complex part.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation of the invention. In the drawings:
FIG. 1 is a diagram illustrating the steps of a method for analyzing the forming quality of a hot-stamped part having a complex shape according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a forming quality analysis method of a hot-stamped part with a complex shape according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The technical solutions of the embodiments can be combined with each other, but it is necessary to be able to realize the basis by those skilled in the art, and the technical solutions of the embodiments can be combined within the scope of the present invention as claimed.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
A forming quality analysis method of a hot-stamped part with a complex shape is shown in figures 1 and 2 and specifically comprises the following steps:
step 1: establishing a three-dimensional model of a hot stamping part with a complex shape;
step 2: extracting position information of all points of the hot stamping part with the complex shape and coordinate information comprising three coordinate axis directions of x, y and z, and establishing a three-dimensional point set information database;
and step 3: dividing part section slices according to position information of all points of the hot stamping part with the complex shape, extracting three adjacent part section slices to form a slice combination, and constructing a slice combination database;
selecting one coordinate axis direction of x, y and z as a section direction, wherein a set of three-dimensional points corresponding to each coordinate value on the coordinate axis is a section slice, selecting three adjacent section slices with equal intervals along the section direction as a slice combination, the section slices in the slice combination are marked as the ith slice, the (i + 1) th slice and the (i + 2) th slice, and i is an integer greater than or equal to 1.
And 4, step 4: sequentially extracting coordinate information of the slice combination to perform traversal operation; when the current slice is the ith slice, i +1 and i +2 are a slice combination, if the current slice is the ith +1 slice, i +1, i +2 and i +3 are adjacent slice combinations of the slice combination A; when the coordinate information of the slice combination is extracted, the position information of each slice in the slice combination is also extracted at the same time so as to facilitate the subsequent analysis;
and 5: constructing a slice coordinate information database;
and 6: correlating the relation between the characteristic information and the position information of the single slice and performing traversal operation;
extracting coordinate information of three continuous three-dimensional points in each single slice according to the position sequence, identifying the connection characteristics of the three coordinates as line segments or circular arcs as characteristic information, extracting the position information of the three continuous three-dimensional points, and associating the characteristic information with the position information, wherein a slice coordinate information database comprises the coordinate information of all three-dimensional points in a current group of slice combinations, and stores the coordinate information of one group of slice combinations each time;
and 7: constructing a slice characteristic database and storing the associated slice characteristic information and position information data;
and 8: judging whether the traversing of the slice coordinate information database is completed or not, and if so, entering a step 9; if the traversal is not completed, returning to the step 6; traversing from the first slice starting point of the current slice combination to the last slice end point of the current slice combination, and then completing the traversal of the slice coordinate information database;
and step 9: utilizing the data of the characteristic database to carry out machine self-learning and form a characteristic identification evaluation model;
selecting a specific amount of feature information from a slice feature database to construct a data set with geometric features of a basic stamping part, and performing feature recognition training by adopting a feature recognition algorithm of machine learning, wherein the learning method adopts a deep learning method to finish automatic feature recognition; by learning a large number of characteristics, coordinate data and stamping part types, a training set is 80%, and a prediction set is 20%; a feature recognition evaluation model is formed, the geometric features of the data set with the geometric features of the basic stamping parts comprise line segment features and arc features, feature recognition training is carried out by adopting a feature recognition algorithm of machine learning, and the specific method for forming the feature recognition evaluation model is that in each slice combination, line segments or arcs are subjected to associated recognition in the same slice, and the line segments or arcs with the same features are spliced into line segments or arcs with larger sizes; performing correlation identification on line segments or circular arc characteristics between every two adjacent slices, splicing the line segments or circular arcs with the same characteristics into a plane or a circular arc surface, and splicing the plane or the circular arc surface with the same characteristics in a slice combination into a larger plane or a larger circular arc surface as a characteristic identification evaluation model; when the characteristic is a line segment or a plane, the same slope is regarded as the same characteristic; when the characteristic is an arc or an arc surface, the circle center and the curvature are the same, and the characteristic is considered to be the same;
step 10: judging whether each feature data of the feature database conforms to the feature identification evaluation model, and if so, entering the step 11; if the data do not meet the requirement, inputting the characteristic data into a step 9 for machine self-learning; the evaluation is carried out by using the formula that the positive examples belong to the same characteristics and the negative examples do not belong to the same characteristics:
wherein:
TP (true Positive): indicating the number of times of judging as positive example and judging correctly;
FP (false positive) which indicates the number of times of judging as positive but judging as wrong;
tn (true negative): the number of times of judging as negative example and judging as correct is shown;
FN (false negative) indicates the number of times of judgment errors when a negative example is judged.
The model is judged to be good or bad by using Accarcy (which may be 0.99) as a judgment criterion.
Step 11: establishing a characteristic identification model database for the characteristic data which accord with the characteristic identification evaluation model;
step 12: judging whether the traversal of the slice combination database is completed or not, and entering a step 13 if the traversal is completed; if not, returning to the step 4; traversing the slice combination database when the first slice combination extracted from the three-dimensional point set information database to the last slice combination extracted from the three-dimensional point set information database is completed;
step 13: performing feature evaluation and integration on the feature recognition model;
the method comprises the steps of splicing the same features in a current slice combination and an adjacent slice combination in a feature recognition model database, comparing the geometric shape of the spliced plane or curved surface at the same position as an original three-dimensional model with a certain actual error, comparing the actual error with a set error, keeping the actual error if the actual error is within the set error range, removing the slice combination adjacent to the current slice combination if the actual error is outside the set error range, and then splicing the same features of the current slice combination and the next slice combination of the adjacent slice combination.
Step 14: dividing the original hot stamping part with the complex shape into a combination of stamping parts with basic shapes;
step 15: and outputting the combination of the basic shape stamping parts and carrying out subsequent finite element simulation analysis.
In a specific embodiment, a three-dimensional model is built for a hot-stamped part with a complex shape, position information and coordinate information of all points of the part with the complex shape are derived by using three-dimensional drawing software such as Meshlab, and a three-dimensional point information database containing x, y and z coordinates is built. Selecting a section slice where an x initial coordinate point is located as a first section slice along the x direction by taking the x-axis direction as the section direction, setting the distance r between adjacent section slices, wherein the value of r is determined according to the calculation precision and the unit can be centimeter, millimeter or micrometer, dividing the section slices of the part according to the position information of all points of the hot stamping part with a complex shape, extracting three adjacent section slices of i, i +1 and i +2 to form a section combination, constructing a section combination database, sequentially extracting the coordinate information of the section combination to perform traversal operation, constructing a section coordinate information database in the extracted current section combination, loading all point sets on the ith section, scanning the ith section combination from the first point of the point set to the last point on the other side point by point, extracting the characteristic information between the adjacent three points in the scanning process, and judging that the characteristic is a line segment or a circular arc, associating the characteristic information with the previously extracted slice position information, constructing a slice characteristic database, storing the associated slice characteristic information and position information data, judging whether the traversal of the slice coordinate information database is finished or not, and entering a machine self-learning stage if the traversal of the slice coordinate information database is finished; if the traversal is not finished, continuously loading an i +1 th slice point set along the x direction, repeating the traversal process of the ith slice, then loading an i +2 th slice along the x direction for traversal identification, selecting a specific number of feature data from a slice feature database, wherein the feature data comprise line segment features and circular arc features, performing feature identification training by adopting a feature identification algorithm of machine learning, and forming a feature identification evaluation model by a specific method that in each slice combination, in the same slice, line segments or circular arcs are subjected to associated identification, and line segments or circular arcs with the same features are spliced into line segments or circular arcs with larger size; performing correlation identification on line segments or circular arc characteristics between every two adjacent slices, splicing the line segments or circular arcs with the same characteristics into a plane or a circular arc surface, splicing the plane or circular arc surface with the same characteristics in a slice combination into a larger plane or circular arc surface as a characteristic identification evaluation model, performing identification evaluation according to the characteristic identification evaluation model in a slice characteristic database, regarding the plane or circular arc surface with the same characteristics as a positive example and the plane or circular arc surface without the same characteristics as a negative example, then judging according to a formula in step 10, establishing a characteristic identification model database according to the identified characteristic data, judging whether the current slice combination database completes traversal, if not, extracting the adjacent slice combination of the current slice combination for traversal, if so, performing characteristic evaluation and integration on the characteristic identification model, and splicing the same characteristics in the current slice combination and the adjacent slice combination, the spliced plane or curved surface has certain actual error compared with the geometric shape of the same position of the original three-dimensional model, the actual error is compared with the set error, if the actual error is within the set error range, the actual error is kept, if the actual error is outside the set error range, the slice combination adjacent to the current slice combination is removed, then the current slice combination is spliced with the next slice combination of the adjacent slice combinations by the same characteristic, the original hot stamping part with the complex shape is divided into a hot stamping part combination with the basic shape, the shape of the part is gradually transited from a box-shaped part, a spherical part and a cup-shaped part to a U-shaped part, a V-shaped part and a sheet body stretching part, finally, a three-dimensional point set is marked as a plurality of simple-shape three-dimensional characteristics, differential processing on the part with the complex shape is realized, and the hot stamping part combination with the basic shape is output for subsequent forming quality finite element analysis of the part.
The original hot stamping part with the complex shape is divided into the hot stamping part combination with the basic shape, and the relative position of each feature and the whole part of the part and the interaction of each feature and the peripheral features are quantitatively evaluated, so that the forming prediction distribution of the simple three-dimensional features can reflect the real situation more accurately.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (8)
1. A forming quality analysis method of a hot stamping part with a complex shape is characterized by comprising the following steps:
step 1: establishing a three-dimensional model of a hot stamping part with a complex shape;
step 2: extracting position information of all points of the hot stamping part with the complex shape and coordinate information comprising three coordinate axis directions of x, y and z, and establishing a three-dimensional point set information database;
and step 3: dividing part section slices according to position information of all points of the hot stamping part with the complex shape, extracting three adjacent part section slices to form a slice combination, and constructing a slice combination database;
and 4, step 4: sequentially extracting coordinate information of the slice combination to perform traversal operation;
and 5: constructing a slice coordinate information database;
step 6: correlating the relation between the characteristic information and the position information of the single slice and performing traversal operation;
and 7: constructing a slice characteristic database and storing the associated slice characteristic information and position information data;
and step 8: judging whether the traversal of the slice coordinate information database is completed or not, and if so, entering a step 9; if the traversal is not completed, returning to the step 6;
and step 9: utilizing the data of the characteristic database to carry out machine self-learning and form a characteristic identification evaluation model;
step 10: judging whether each feature data of the feature database conforms to the feature identification evaluation model, and if so, entering the step 11; if the data do not meet the requirement, inputting the characteristic data into a step 9 for machine self-learning;
step 11: establishing a feature recognition model database for feature data conforming to the feature recognition evaluation model;
step 12: judging whether the traversal of the slice combination database is completed or not, and entering a step 13 if the traversal is completed; if not, returning to the step 4;
step 13: performing feature evaluation and integration on the feature recognition model;
step 14: dividing the original hot stamping part with the complex shape into a combination of stamping parts with basic shapes;
step 15: and outputting the combination of the basic shape stamping parts and carrying out subsequent finite element simulation analysis.
2. The forming quality analysis method for the hot-stamped part with the complicated shape according to claim 1, wherein in the step 3, the sectional slices of the part are divided according to the position information of all points of the hot-stamped part with the complicated shape, and the method for extracting the combination of the three adjacent sectional slices of the part is to select one coordinate axis direction of x, y and z as the sectional direction, the set of three-dimensional points corresponding to each coordinate value on the coordinate axis is a sectional slice, and select three adjacent sectional slices with equal intervals along the sectional direction as a slice combination, wherein the sectional slices in the slice combination are marked as the ith slice, the (i + 1) th slice and the (i + 2) th slice, and i is an integer greater than or equal to 1.
3. The method for analyzing the forming quality of a hot-stamped part with a complicated shape according to claim 1, wherein the step 6 of correlating the feature information and the position information of the single slices is to extract three continuous feature coordinates in each single slice in a positional order, identify three coordinate points connecting features as line segments or circular arcs as the feature information, extract the position information of the three continuous feature coordinates, and correlate the feature information with the position information.
4. The method for analyzing the forming quality of the hot-stamped part with the complicated shape according to claim 1, wherein the step 9 is implemented by utilizing the data of the feature database for self-learning of the machine and forming the feature recognition and evaluation model through a specific method of selecting a specific amount of feature information from the feature database to construct a data set with geometric features of a basic stamping part, and performing feature recognition training by utilizing a feature recognition algorithm of machine learning and forming the feature recognition and evaluation model.
5. The method for forming quality analysis of hot-stamped parts of complex shape according to claim 4, wherein the geometric features that build the dataset with the geometric features of the base stamping include line segment features and arc features.
6. The forming quality analysis method of a hot-stamped part with a complex shape according to claim 5, characterized in that feature recognition training is performed by using a feature recognition algorithm of machine learning, and a specific method for forming a feature recognition evaluation model is that in each slice combination, in the same slice, line segments or arcs are subjected to associated recognition, and line segments or arcs with the same features are spliced into line segments or arcs with a larger scale; and performing correlation identification on line segments or circular arc characteristics between every two adjacent slices, and splicing the line segments or circular arcs with the same characteristics into a plane or a circular arc surface.
7. The method for analyzing the forming quality of a hot-stamped part with a complicated shape according to claim 1, wherein the step 10 of determining whether the feature data conforms to the feature recognition evaluation model is to evaluate whether the feature data belongs to positive examples and negative examples which have the same feature, and the feature data belongs to the negative examples, by using a formula:
wherein:
TP (true Positive): indicating the number of times that the judgment is positive and correct;
FP (false positive) which indicates the number of times of judging as positive but judging as wrong;
tn (true negative): indicating the number of times the judgment is negative and correct;
FN (false negative) indicates the number of times of determination errors when a negative case is determined.
8. The method for analyzing the forming quality of a hot-stamped part with a complex shape according to claim 1, wherein the feature evaluation and integration of the feature recognition model in step 13 is performed by splicing the same features in the current slice combination and the adjacent slice combination in the feature recognition model database, comparing the spliced features with a set error, if the spliced features are within the set error range, retaining the spliced features, and if the spliced features are outside the set error range, removing the slice combination adjacent to the current slice combination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210243169.4A CN114662232A (en) | 2022-03-11 | 2022-03-11 | Forming quality analysis method for hot stamping part with complex shape |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210243169.4A CN114662232A (en) | 2022-03-11 | 2022-03-11 | Forming quality analysis method for hot stamping part with complex shape |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114662232A true CN114662232A (en) | 2022-06-24 |
Family
ID=82029979
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210243169.4A Pending CN114662232A (en) | 2022-03-11 | 2022-03-11 | Forming quality analysis method for hot stamping part with complex shape |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114662232A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115027087A (en) * | 2022-08-09 | 2022-09-09 | 江苏艾卡森智能科技有限公司 | Quality analysis system for motor magnetic shoe stamping process |
-
2022
- 2022-03-11 CN CN202210243169.4A patent/CN114662232A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115027087A (en) * | 2022-08-09 | 2022-09-09 | 江苏艾卡森智能科技有限公司 | Quality analysis system for motor magnetic shoe stamping process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7542889B2 (en) | Determination of a model of a geometry of a metal sheet forming stage | |
| US20220118501A1 (en) | In-Situ Springback Compensation In Incremental Sheet Forming | |
| CN110516320B (en) | Matching analysis method and device suitable for train body assembly parts | |
| CN116402866A (en) | Point cloud-based part digital twin geometric modeling and error assessment method and system | |
| CN105868428A (en) | Springback compensation method of stamped part | |
| CN114743259A (en) | Pose estimation method, pose estimation system, terminal, storage medium and application | |
| CN114662232A (en) | Forming quality analysis method for hot stamping part with complex shape | |
| CN113987705A (en) | Automobile covering part rebound prediction method based on deep learning | |
| CN109344498B (en) | Design implementation method of wedge module | |
| CN111014415A (en) | Method for manufacturing draw bead based on CAE technology | |
| CN113333559B (en) | Stamping covering part springback analysis and compensation method based on Autoform software | |
| CN113283162B (en) | Plastic optical lens surface shape error prediction method, electronic device and storage medium | |
| US11651120B2 (en) | Method and system of reporting stretching failure in stamping die development | |
| CN111639406B (en) | Method for optimizing shape of time sequence flanging tool knife edge | |
| CN109388875A (en) | A kind of design implementation method of elastic element module | |
| CN116091496B (en) | Defect detection method and device based on improved Faster-RCNN | |
| CN110851920B (en) | Automatic generation method of main reinforcement line of die material pressing device | |
| CN110287520B (en) | Automatic recognition method for punching elements | |
| CN107092745A (en) | A kind of window lifting plate forming technology optimization method based on variance analysis | |
| US8233694B2 (en) | Method of appearance deformation indexing | |
| CN115270426A (en) | Stamping springback compensation control method | |
| Adrian et al. | Curating Datasets of Flexible Assemblies to Predict Spring-Back Behavior for Machine Learning Purposes | |
| CN114155522A (en) | Point cloud data quality inspection repairing method and system | |
| CN107563029B (en) | Support vector machine approximate model optimization method based on K-fold cross verification method | |
| CN112307673A (en) | Grid surface quality detection method based on deep learning |
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 |