Injection molding technology optimization method based on GRNN (Genera-lized Regression Neural Network) and injection molding technology
A neural network and process optimization technology, applied in neural learning methods, biological neural network models, design optimization/simulation, etc., can solve problems such as poor convergence, many injection molding process parameters, and slow network training.
Inactive Publication Date: 2018-04-20
柳州市城中区聚宝机械冲压厂
View PDF2 Cites 14 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Based on this, it is necessary to provide an injection molding process optimization method and injection molding process based on GRNN neural network for the problems of many parameters adjustment, slow network training and poor convergence in the injection molding process of automotive interior panels based on BP neural network.
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
[0039] see Figure 1 to Figure 4 As shown, the injection molding process optimization method based on the GRNN neural network of an embodiment of the present invention comprises the following steps:
[0040] S100, establishing a CAE analysis model of the injection molding product;
[0041] S200, using CAE software to simulate the injection molding process parameters of the CAE analysis model, and determine the types of injection molding process parameters that affect the injection molding product to cause injection defects;
[0042] S300, converting the types of injection molding process parameters into types of control parameters;
[0043] S400, based on the type of control parameters, use the GRNN neural network to perform network training to obtain the final optimized control parameters.
[0044] The above injection molding process optimization method based on GRNN neural network uses GRNN neural network (Generalized Regression Neural Network, Genera-lized Regression Neur...
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
| Property | Measurement | Unit |
|---|---|---|
| thickness | aaaaa | aaaaa |
| area | aaaaa | aaaaa |
Login to View More
Abstract
The invention provides an injection molding technology optimization method based on a GRNN (Genera-lized Regression Neural Network). The method includes the following steps: establishing a CAE analysis model of an injection molding product; utilizing CAE software to simulate injection molding technology parameters of the CAE analysis model, and determining injection molding technology parameter types making the injection molding product produce injection molding defects; converting the injection molding technology parameter types into control parameter types; and utilizing the GRNN to carry out network training on the basis of the control parameter types to acquire final optimized control parameters. According to the above-mentioned injection molding technology optimization method based onthe GRNN, the GRNN is utilized to carry out network training, and compared with other neural networks, especially BP neural-networks, the GRNN invokes few parameters, is faster in network training speed, is improved in convergence, and can improve accuracy of injection molding technology parameter optimization.
Description
technical field [0001] The invention relates to the field of injection molding technology, in particular to a GRNN neural network-based injection molding process optimization method and an injection molding process. Background technique [0002] Among the automotive interior plastic parts, there are many slender and special-shaped products, such as interior trim strips, air-conditioning vent grilles, armrest strips, etc. The biggest problem of injection molding of these products is deformation, and most of them are warping deformation. There are four main causes of warping deformation: uneven cooling, uneven shrinkage, inconsistent molecular orientation, and corner effects. The influence ratios of the four factors are different, and it is difficult to find out the relationship between them and the injection molding control elements of the injection molding machine. This relationship is a nonlinear control relationship, so it needs to be optimized, analyzed and controlled wit...
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 Applications(China)
IPC IPC(8): G06F17/50G06N3/08
CPCG06F30/15G06F30/20G06F2119/18G06N3/08
Inventor 唐西西邓其贵王晶晶梁德坚黄力
Owner 柳州市城中区聚宝机械冲压厂