Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

NURBS curve adaptive interpolation method based on BP neural network

A BP neural network, self-adaptive technology, applied in the direction of instruments, computer control, simulators, etc., can solve the problems of complex calculation process of interpolation parameters and large amount of calculation.

Pending Publication Date: 2021-04-09
DALIAN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of complex calculation of interpolation parameters and large amount of calculation in the process of spline curve interpolation, a non-uniform rational B-spline curve (NURBS) interpolation method based on BP neural network is proposed. By establishing a neural network NC interpolation model, the calculation process of interpolation parameters is optimized; with the bow height error as a constraint condition, the processing speed is effectively planned

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
  • NURBS curve adaptive interpolation method based on BP neural network
  • NURBS curve adaptive interpolation method based on BP neural network
  • NURBS curve adaptive interpolation method based on BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] The present embodiment provides a kind of NURBS curve self-adaptive interpolation method based on BP neural network, specifically comprises:

[0059] According to the mathematical definition of the curve, to define a NURBS curve, it is necessary to determine its control vertices, weight factors and node vectors;

[0060]

[0061] Interpolation is performed according to the change of the parameter increment, and the increment is constrained by the curve bow height error; the bow height error is the maximum distance between the arc and the chord generated by connecting two endpoints on the curve, which is one of the key factors affecting the machining accuracy. When performing interpolation, the arc approximation method is used to calculate the relationship between the bow height error, the feed speed and the curvature of the curve, and the radius of curvature is used to limit the bow height error. The small arc segment at an interpolation point C(p) on the curve is tr...

example

[0096] Example: Select a two-dimensional NURBS curve to simulate on the MATLAB platform. The control points of the curve part are: (150,150),(0,0),(0,300),(150,150),(300,0),(300,300),(150,150). The parameters of the experimental design during simulation are: programming speed F=0.06m / s, maximum allowable acceleration A=0.006m / s2, sampling period and interpolation period T=2ms, and the maximum bow height error of constraints is 0.002mm.

[0097] The error curve obtained is lower than that before using the above method, which shows the feasibility and effectiveness of the invention. The method of the invention can maintain the stability of the speed while realizing higher precision and efficient processing, and can realize the stable and efficient processing of the machine tool.

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 an NURBS curve adaptive interpolation method based on a BP neural network. The method comprises the following steps: determining a sample set for training a BP neural network numerical control interpolation model; obtaining the number of hidden layer nodes and calculating the input and output weighted sum of each node; calculating the input and output weighted sum of output layer nodes; obtaining the output result of the output layer again; obtaining an output error of the hidden layer according to the output error of the output layer; updating and resetting the connection weight and the critical value according to an error result of the output layer and the hidden layer until the connection weight and the critical value are smaller than the error result; and repeating the above steps, inputting samples in the sample data set to train the BP neural network, and completing multiple iterations until an output result meets an expected value. According to the method, the neural network numerical control interpolation model is established, and the calculation process of interpolation parameters is optimized; and the machining speed is effectively planned by taking the bow height error as a constraint condition.

Description

technical field [0001] The invention relates to the field of numerical control machine tool processing, in particular to a BP neural network-based NURBS curve self-adaptive interpolation method. Background technique [0002] In the computer numerical control system, the processing of complex curves and curved surface parts has always been a difficult point. Traditional CNC machining uses CAD / CAM system to discretize complex curves to be processed into a large number of tiny straight line segments, and then use these straight line segments to approximate and fit the curves to be processed. However, with the continuous development of numerical control technology, the spline interpolation method has gradually replaced the original linear interpolation and circular interpolation functions, and has become the main interpolation method. [0003] Many scholars have conducted a lot of in-depth research on the function of spline curve interpolation and achieved good progress and res...

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): G05B19/408G05B19/41G05B19/416
CPCG05B19/4083G05B19/41G05B19/4163G05B2219/43001G05B2219/45136
Inventor 盖荣丽仓艳
Owner DALIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com