Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for predicting forming quality of internal threads of copper tubes on basis of BP (back-propagation) neural network algorithms

A BP neural network and neural network technology, applied in the field of copper internal thread quality prediction, can solve problems such as insufficient analysis

Inactive Publication Date: 2017-01-04
QUZHOU UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Zhang Guangliang et al. analyzed the causes of folding defects in the TP2 internal thread forming process, and concluded that the gap between the tube blank and the thread core is the cause of the folding, but did not link this factor with the specific forming process parameters , the analysis is not deep enough

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
  • Method for predicting forming quality of internal threads of copper tubes on basis of BP (back-propagation) neural network algorithms
  • Method for predicting forming quality of internal threads of copper tubes on basis of BP (back-propagation) neural network algorithms
  • Method for predicting forming quality of internal threads of copper tubes on basis of BP (back-propagation) neural network algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] (1) Determine the three independent variables of the BP neural network model as motor speed, drawing speed and spinning position, and a dependent variable internal thread tooth height. The number of input layer nodes of the BP neural network is set to 3, and the number of output layer nodes is Set to 1.

[0030] (2) The number of nodes in the hidden layer is based on the empirical formula 2n+1 proposed by Hecht-Nielsen (n is the number of nodes in the input layer), 5, 7 and 9 are selected respectively, the training target is 0.00001, and the learning rate is 0.1.

[0031] (3) The BP neural network adopts the network structure of 3-7-1.

[0032] (4) Normalize the training samples and test samples so that the input and output data are mapped within [0.1,0.9].

[0033] The calculation method of normalization processing of training samples is as follows:

[0034] x i = 0.8 ( x ...

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 relates to a method for predicting the forming quality of internal threads of copper tubes on the basis of BP (back-propagation) neural network algorithms, and belongs to the field of technologies for predicting the quality of internal threads of copper tubes. The method has the advantages that the method for predicting the forming quality of the internal threads of the copper tubes at early manufacturing stages is easy to apply and high in efficiency, and the quality of the internal threads can be controlled; three elements including the rotational speed, the drawing speed and the spinning location of a motor are used as independent variables, tooth heights of the internal threads are used as dependent variables, BP neural networks on the basis of genetic algorithms are constructed by the aid of the independent variables and the dependent variables, the forming quality of the internal threads can be predicted by the aid of the BP neural networks, complicated mathematical modeling problems are transformed into problems for solving network connection weights and thresholds from discrete experimental data by means of training and learning, system models which can reflect various main technological parameters and forming quality inherent laws in internal thread forming procedures are built, and accordingly effective ways can be provided for predicting the forming quality and defects of the internal threads.

Description

technical field [0001] The invention belongs to the technical field of copper internal thread quality prediction, and mainly relates to a method for predicting the forming quality of copper pipe internal thread based on BP neural network algorithm. Background technique [0002] According to the national sustainable development requirements and the Twelfth Five-Year Plan, the air-conditioning manufacturing industry is developing in the direction of energy saving, environmental protection and health. Phosphorus deoxidized copper No. 2 (TP2) is widely used in heat exchangers, fuel systems, air restrictors and pump pipes and other deep drawn and welded parts because of its good thermal conductivity, corrosion resistance and excellent processability Among them, especially in the air-conditioning industry, it is very popular. [0003] TP2 internal thread copper tube has good thermal conductivity, anti-magnetic, corrosion resistance and excellent processing performance, widely use...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/02G06N3/08
CPCG06N3/02G06N3/084G06N3/086
Inventor 姜春娣
Owner QUZHOU UNIV