A Rapid Prediction Method of Sheet Metal Extrusion Forming Force Based on Parametric Compression of Mixed Materials
A technology of extrusion forming and prediction method, which is applied in the direction of electrical digital data processing, instrumentation, geometric CAD, etc., can solve the problems of falling into local minimum, over-fitting, etc., achieve fast and accurate prediction, reduce quantity, and improve design efficiency Effect
Active Publication Date: 2022-07-12
SHANGHAI JIAOTONG UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Aiming at the above-mentioned deficiencies in the prior art, the present invention proposes a rapid prediction method of sheet metal extrusion forming force based on the parameter compression of mixed materials, which is based on the method of unsupervised learning and supervised learning of neural network, and overcomes the problems of neural network with many features and data In the scene with a small amount, it is easy to fall into local minimum, overfitting and other problems, which improves the prediction accuracy of the model and can provide strong support for the sheet metal extrusion process and die design
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0034] like figure 1 As shown, the present embodiment relates to a method for rapidly predicting the extrusion forming force of sheet metal by parameter compression of mixed materials, which specifically includes the following steps:
[0035] Step 1: Obtain different types of material stress-strain relationship data by setting different types of model coefficients in the undetermined coefficient space of different material constitutive models.
[0036] The aforementioned constitutive model adopts the large-strain material constitutive model commonly used in sheet metal extrusion, including:
[0037] ①Ludwik:σ=A+B·(ε p ) n
[0038] ②Swift: σ=A·(B+ε p ) n
[0039] ③Ghosh: σ=A·(B+ε p ) n -C
[0040] ④Hockett-Sherby: σ=B-(B-A)·exp(-C·(ε p ) n )
[0041] ⑤Voce: σ=B-(B-A) exp(-C ε p ), where: σ is the flow stress of the material, ε p is the equivalent plastic strain, and A, B, C, and n are undetermined coefficients.
[0042] A large number of σ(ε) data for different m...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
A rapid prediction method of sheet metal extrusion forming force for parameter compression of mixed materials, which forms an autoencoder through an unsupervised learning algorithm, makes full use of the existing constitutive models of different materials under large strain, compresses the material flow stress curve, and constructs material parameters Compress the model to obtain the material performance characteristics after compression; and then establish a complex nonlinear relationship between material performance characteristics, process parameters and sheet extrusion force through supervised learning, so as to achieve rapid and accurate sheet extrusion force. Prediction, the present invention is based on the method of unsupervised learning and supervised learning of neural network, which overcomes the problem that neural network is prone to fall into local minimum value and overfitting in scenarios with many features and small amount of data, and improves the prediction of the model. Accuracy can provide strong support for sheet extrusion process and die design.
Description
technical field [0001] The invention relates to a technology in the field of material forming, in particular to a method for rapidly predicting the extrusion forming force of sheet metal by parameter compression of mixed materials. Background technique [0002] The existing prediction methods of sheet metal extrusion forming force mainly include mechanical analysis method and numerical simulation method. In the process of sheet extrusion, the size of the forming force is not only affected by the mechanical properties of the material itself, but also by many process parameters. The mechanical analysis method is widely used in engineering, but it mainly draws on the model of bar extrusion. The error is large. The numerical simulation method can effectively improve the prediction accuracy of the forming force, but the finite element modeling process is cumbersome, requires special software, cannot obtain the results quickly, and is difficult to promote in engineering. In rece...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/23G06F30/17G06F113/24G06F119/14
CPCY02P90/30
Inventor 曹益旗向华庄新村赵震
Owner SHANGHAI JIAOTONG UNIV