Calcium carbonate filled composite material design method based on BP neural network

A BP neural network and composite material technology, which is applied in neural learning methods, biological neural network models, computer-aided design, etc. Composite material structure and performance design and other issues, to achieve the effect of improving R&D efficiency and shortening the R&D cycle

Pending Publication Date: 2021-06-29
HEZHOU UNIV
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, only using the finite element calculation results as the data set for machine learning model training and testing will affect the accuracy and applicability of the resulting machine

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Calcium carbonate filled composite material design method based on BP neural network
  • Calcium carbonate filled composite material design method based on BP neural network
  • Calcium carbonate filled composite material design method based on BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] like figure 1 As shown, the design method of calcium carbonate filled composite material based on BP neural network in this embodiment includes the following steps:

[0050] Step S1: Design a multi-factor and multi-level orthogonal test, and prepare test samples

[0051] Table 1 Orthogonal test factor and level table

[0052]

[0053] Table 2 L9(3 3 ) test plan

[0054]

[0055] Operate according to the orthogonal test design scheme in Table 1 and Table 2. First, weigh 10kg of calcium carbonate with different particle sizes, then add an equal amount of surface modifier and mix thoroughly to form a layer of wrapping on the surface of the calcium carbonate particles. Then, the surface-modified calcium carbonate particles are added to the PVC matrix for mixing, placed in an ultrasonic oscillator or a high-speed mixer with a speed of not less than 3000 rpm, and stirred at a temperature of 100 ° C for 50 minutes to make Disperse uniformly, then cool down to below 4...

Embodiment 2

[0083] like figure 1 As shown, the method for predicting the mechanical properties of calcium carbonate filled composite materials based on reverse modeling in this embodiment includes the following steps:

[0084] Step S1: Design a multi-factor and multi-level orthogonal test, and prepare test samples

[0085] Operate according to the orthogonal test design scheme in Table 1 and Table 2. First, weigh 10kg of calcium carbonate with different particle sizes, then add an equal amount of surface modifier and mix thoroughly to form a layer of wrapping on the surface of the calcium carbonate particles. Then, the surface-modified calcium carbonate particles are added to the PP matrix for mixing, placed in an ultrasonic oscillator or a high-speed mixer with a speed of not less than 3000 rpm, and stirred at 120 ° C for 30 minutes to make Disperse uniformly, then cool down to below 40°C and discharge for later use; then add the above-mentioned ready-to-use mixture into the co-rotating...

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

No PUM Login to view more

Abstract

The invention discloses a design method of a calcium carbonate filled composite material based on a BP neural network. The design method comprises the following steps: preparing a test sample; testing mechanical property parameters; generating a representative volume unit, and calculating a three-dimensional box dimension; collecting various different filling process parameters and corresponding mechanical property indexes, and sorting into a data set; carrying out BP neural network system modeling; optimizing the initial BP neural network by adopting a GA (Genetic Algorithm), and training the model by utilizing a training set in the data set; calculating an error percentage; the BP neural network model can be used for process design and performance prediction of the calcium carbonate filled composite material. According to the method, the defect that a two-dimensional image is difficult to reflect representative volume unit structure characteristics under different filling process parameters can be overcome, the filling process parameters of the calcium carbonate powder filled polymer-based composite material are scientifically designed, the design, research and development efficiency of the calcium carbonate powder filled polymer-based composite material is improved, and the research and development period can be shortened to half.

Description

technical field [0001] The invention relates to a calcium carbonate filling composite material design method based on BP neural network, which is suitable for the process design and structure and performance prediction of calcium carbonate powder filling polymer matrix composite material, and belongs to the technical field of composite material manufacturing. Background technique [0002] Calcium carbonate powder (CaCO 3 ) are filled polymer matrix composites (e.g. CaCO 3 / PVC, CaCO 3 It can not only reduce the amount of polymer matrix and cost, but also improve the strength, toughness, hardness, elastic modulus, dimensional stability, etc. of composite materials. Calcium carbonate powder-filled composite materials need to have good comprehensive mechanical properties such as tensile strength, toughness, impact strength and bending strength to meet the needs of different application fields. [0003] There are many technological factors that affect the mechanical propertie...

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
no application Login to view more
IPC IPC(8): G06F30/20G06N3/08G06N3/12G06F113/26
CPCG06N3/084G06N3/126G06F30/20G06F2113/26
Inventor 潘斯宁罗士君苏南光胡正西张敏
Owner HEZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap