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

Analysis method for blade root stress based on neural network algorithm

A neural network algorithm and stress analysis technology, applied in the field of steam turbine blades, can solve the problems of slow three-dimensional nonlinear large deformation, etc., and achieve the effect of solving slow calculation speed and solving a large amount of pre-processing work

Active Publication Date: 2017-03-15
XI AN JIAOTONG UNIV
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for analyzing blade root stress based on a neural network algorithm, so as to solve the problem that the existing finite element method solves the three-dimensional nonlinear large deformation problem too slowly

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
  • Analysis method for blade root stress based on neural network algorithm
  • Analysis method for blade root stress based on neural network algorithm
  • Analysis method for blade root stress based on neural network algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0039] see figure 1 Shown, a kind of blade root stress analysis method based on neural network algorithm of the present invention comprises following five steps:

[0040] 1. Obtain the leaf-root model sample point set learned by the neural network by using the space-reduced fast uniform sequence sampling method.

[0041]For a leaf root that needs n parameters to determine the geometric shape, it is known that there are m training sample points in its design space (each sample point contains a set of parameters that can determine the geometric size of the leaf root, such as carrying surface width, blade root axial length, etc.). After normalizing the n parameters on its design space, the initial parameter matrix X of the leaf root sample can be obtained = {x 1 ,x 2 ,...,x m} T ,in for a sample point. In order to improve the calculation accuracy...

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 analysis method for a blade root stress based on a neural network algorithm. The method comprises the following steps: (1) acquiring a blade root model sample point set for neural network learning by adopting a quick uniform sequence sampling method; (2) completing the parametric modeling for the blade root and the corresponding rim according to the sample point set acquired in the step (1), completing the strength calculation for each blade root-rim model by using finite element software and acquiring a response corresponding to each sample point; (3) reducing the dimensionality of the sample point by adopting a principal component analysis method, simplifying an input vector of the neural network and promoting the generalization ability of the neural network; (4) initializing a neuron model and confirming the quantity of the nerve element of the hidden layer and the input / output vector of the neural network; and (5) training the neural network till meeting a stopping criterion by utilizing sample data of parametric blade root, and then verifying the accuracy and generalization ability of the model by using a test sample. The model constructed according to the method has the advantages of high calculation speed and high calculation precision.

Description

technical field [0001] The invention relates to the field of steam turbine blades, in particular to a blade root stress analysis method. Background technique [0002] For steam turbine blades that have been operating in a harsh environment of high temperature and high pressure, the root of the blade is the main part that bears the centrifugal force. When the stress of a certain part of the blade root reaches a certain value and after a certain period of time, it may cause the blade to break and cause the turbine to fail. , resulting in huge economic losses. [0003] The finite element method is currently the most important calculation method for blade root strength, which divides the entity into a series of units, and then introduces appropriate boundary conditions for solution. This method requires artificial grid division, and it often takes a lot of time to solve the nonlinear large deformation problem of blade root strength calculation, and the accuracy of the calculati...

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): G06F17/50
CPCG06F30/17G06F2119/06G06F30/23
Inventor 张荻郭鼎刘天源谢永慧
Owner XI AN JIAOTONG 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