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

A Relay Quality Fluctuation Suppression Design Method Based on Radial Basis Function Neural Network

A neural network, quality fluctuation technology, applied in biological neural network models, design optimization/simulation, special data processing applications, etc., can solve problems such as inability to eliminate the robustness of the scheme, low optimization accuracy, and inability to determine the global optimal solution.

Active Publication Date: 2022-02-08
HARBIN INST OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem that the current parameter design method of electrical appliances cannot determine the global optimal solution, cannot eliminate the interaction of factors affecting the robustness of the scheme, and the modeling process is complicated, which leads to low optimization accuracy. Design Method of Relay Quality Fluctuation Suppression Based on Functional Neural 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
  • A Relay Quality Fluctuation Suppression Design Method Based on Radial Basis Function Neural Network
  • A Relay Quality Fluctuation Suppression Design Method Based on Radial Basis Function Neural Network
  • A Relay Quality Fluctuation Suppression Design Method Based on Radial Basis Function Neural Network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0021] Specific implementation mode 1: This implementation mode records a design method for relay quality fluctuation suppression based on radial basis function neural network, and the method includes the following steps:

[0022] Step 1: Determine the input parameters and uncertainty factors according to the research object and optimization goal, and carry out the orthogonal test design of the inner and outer surfaces; among them, the input parameters are arranged in the inner table, and the uncertainty factors are arranged in the outer surface, according to the number of input parameters and uncertain parameters and the number of levels respectively select the inner and outer orthogonal tables and determine the test plan; the research object is a relay, and the optimization goal is determined according to the actual situation, which can be the armature pull-in speed, the magnetic retention force, etc.; the input parameters can affect the optimization The size of each key part...

specific Embodiment approach 2

[0029] Specific embodiment 2: A kind of relay quality fluctuation suppression design method based on radial basis function neural network described in specific embodiment 1, in step 3, the decoupling of the parameters is specifically: selecting any input parameter For the non-repetitive combination of two parameters (X, Y), first calculate the changes Δx and Δy of the corresponding output characteristics when the parameters X and Y change independently, and then calculate the change of the corresponding output characteristics when the combination of (X, Y) changes at the same time Quantity Δxy, if parameter X and parameter Y are completely independent, it should satisfy the mathematical relationship of Δxy=Δx+Δy, otherwise it means that there is an interaction between parameter X and parameter Y.

[0030] Define the interaction factor γ to reflect the degree of interaction between parameters X and Y, and use the following formula to determine the interaction between parameters,...

specific Embodiment approach 3

[0033] Specific embodiment three: a kind of relay quality fluctuation suppression design method based on radial basis function neural network described in specific embodiment one, in step five, the described linear regression method is used to establish the polynomial between the adjustment factor and the output characteristic The function is specifically: after the optimization scheme of the stability factor is determined, the output characteristics will deviate with the change of the parameter value, first calculate the offset ΔF of the output characteristics s , and then jointly adjust the factor polynomial F a , to establish the offset compensation target H 2 , as shown in the following formula.

[0034]

[0035] Since the adjustment factor and the stability factor are independent of each other, the output offset can be quantitatively compensated without affecting the robustness of the scheme, and finally the adjustment factor X a design plan.

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

A design method for suppressing quality fluctuation of relays based on radial basis function neural network belongs to the technical field of relay product design. In order to solve the problem that the current parameter design method cannot determine the global optimal solution and cannot eliminate the interaction of factors affecting the robustness of the scheme. The methods are as follows: 1. Determine the controllable factors, error factors and orthogonal test plan; 2. Carry out signal-to-noise ratio and sensitivity significance analysis to determine stable factors; 3. Conduct interactive analysis to determine adjustment factors; 4. Establish stable factors The radial basis function neural network model and the optimization suppression objective function are used to determine the optimal solution of the stability factor. Fifth, the polynomial model of the adjustment factor and the offset compensation objective function are established to determine the optimal solution of the adjustment factor. The invention determines the adjustment factor by decoupling the parameters, and then uses the adjustment factor to compensate the deviation of the output characteristic, so as to realize the adjustment of the output characteristic to the target value without affecting the robustness of the stability factor.

Description

technical field [0001] The invention belongs to the technical field of relay product design, and in particular relates to a design method for suppressing relay quality fluctuations based on a radial basis function neural network. Background technique [0002] Parameter design is an important link in the design process of relay products. It not only directly determines whether the output characteristics of the product can meet the design requirements, but also directly affects the resistance of the product design scheme to external interference, internal interference, manufacturing dispersion and other uncertain factors. Capability, that is, robustness. Therefore, it is of great significance to adopt a reasonable anti-quality fluctuation parameter design method to improve the performance stability and quality consistency of relay products. [0003] The key to robust parameter design is to use the nonlinear nature between input parameters and output characteristics to effecti...

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 Patents(China)
IPC IPC(8): G06F30/27G06N3/02
CPCG06N3/02G06F30/20
Inventor 邓杰吴岳庞晓敏翟国富
Owner HARBIN INST OF TECH
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