Method for reducing full-characteristic space curved surface fitting error based on BP neural network

A BP neural network and surface fitting technology, which is applied in the field of reducing the fitting error of full-featured space surfaces based on BP neural network, and can solve the problems of lack of uniformity of various parameters.

Pending Publication Date: 2020-05-19
LIAONING UNIVERSITY OF PETROLEUM AND CHEMICAL TECHNOLOGY
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current method lacks the uniformity between the parameters. The results of the two network simulations are finally expressed in the same space coordinate system, and there will be obvious misalignment. At this time, this misalignment needs to be improved, but the error always exists. , the analysis of errors is an important part of evaluating the accuracy and reliability of the entire 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for reducing full-characteristic space curved surface fitting error based on BP neural network
  • Method for reducing full-characteristic space curved surface fitting error based on BP neural network
  • Method for reducing full-characteristic space curved surface fitting error based on BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0037] combine figure 1 , the present invention proposes a method for reducing full-character space surface fitting errors based on BP neural network, said method comprising the following steps:

[0038] Step 1. Mathematical expression of the characteristics of the pump turbine: the runner flow Q and the runner moment M of the Francis turbine are related to the water head H of the turbine, the opening of the guide vane α and the runner speed n, and...

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 provides a method for reducing a full-characteristic space curved surface fitting error based on a BP neural network. According to the method, two different BP neural networks are constructed according to two function relations Q11 = fQ (alpha, n11) and M11 = fM (alpha, n11), and the purpose that the unit flow and the unit torque can be determined through a simulation network by giving the guide vane opening degree and the unit rotating speed is achieved. The two network simulation results are finally expressed in the same space coordinate system to have obvious imbalance and lack the uniformity of all parameters, and the imbalance is improved by adjusting the number of network nodes at the moment.

Description

technical field [0001] The invention belongs to the technical field of water turbine full characteristic curve expression, in particular to a method for reducing the fitting error of full characteristic space curved surface based on BP neural network. Background technique [0002] In the final analysis, the space surface description method of the full characteristic curve of the pump turbine is to complete the determination of the characteristic parameters under any working condition. The commonly used methods are the least square method, B-spline function and BP neural network. However, the current method lacks the uniformity between the parameters. The results of the two network simulations are finally expressed in the same space coordinate system, and there will be obvious misalignment. At this time, this misalignment needs to be improved, but the error always exists. , the analysis of the error is an important content to evaluate the accuracy and reliability of the whol...

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): G06F30/17G06F30/20G06N3/04G06N3/08
CPCG06N3/084G06N3/045
Inventor 苏文涛李洋
Owner LIAONING UNIVERSITY OF PETROLEUM AND CHEMICAL TECHNOLOGY
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