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

Device and method for multi-point vibration response frequency domain prediction based on support vector machine

A support vector machine and multi-point vibration technology, which is applied in vibration testing, measuring devices, testing of machine/structural components, etc., can solve problems such as difficulty in obtaining system modeling transfer functions, difficulty in measurement, and impossibility

Active Publication Date: 2020-06-09
HUAQIAO UNIVERSITY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has two major disadvantages: first, for complex engineering structures, it is not easy to model the system and obtain the transfer function; second, it is very difficult or even impossible to measure the load case

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
  • Device and method for multi-point vibration response frequency domain prediction based on support vector machine
  • Device and method for multi-point vibration response frequency domain prediction based on support vector machine
  • Device and method for multi-point vibration response frequency domain prediction based on support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] Embodiment 1: a kind of experimental device that multi-source load is applied jointly, such as figure 2 As shown, the vibration structure adopted is a fixed disc, which has a relatively large damping ratio and can be regarded as a nonlinear time-invariant structure. Two irrelevant excitation sources are used, one is the exciter excitation, and the other is the PCB hammer hammer excitation, that is, the irrelevant excitation source m=2, the experiment does not need to record the vibration excitation data of the excitation table and The excitation data of the hammer, but the unknown and direction of the excitation point of the excitation table and the excitation point of the hammer are required to be fixed, so as to ensure that the system is a time-invariant system. Six sensors are used to measure the vibration of the simply supported beam, which can reflect the main vibration direction of the beam. Two of the six sensors are used as unknown node sensors to predict the ...

Embodiment 2

[0080] Embodiment 2: A method for generating historical experimental data for multi-point vibration response frequency domain prediction under the condition of unknown load, see Figure 3 to Figure 7 ; The independent spherical noise excitation source excitation has 3 magnitudes of excitation, and the magnitude gradually increases; the vibration excitation of the independent suspension vibration table vibrator has 5 magnitudes of excitation, and the magnitude Gradually increase; when the noise excitation and vibration excitation are jointly loaded, the magnitudes of the noise excitation and vibration excitation are combined in pairs to form 15 different magnitudes, thus realizing the simulation of complex acoustic vibration environments for response prediction tests Research. Load the joint excitation of 15 different levels of noise excitation and vibration excitation on the acoustic vibration experimental device, respectively measure the excitation force of the vibration exci...

Embodiment 3

[0081] Embodiment 3: a kind of multi-point vibration response frequency domain prediction method based on support vector machine, because historical data has 14 groups altogether, the number of all measuring points is 9, at first n=9 response measuring points are grouped, choose n 1 =The response data of 7 measuring points is used as the response data of known measuring points, n 2 =The response data of 2 measuring points is used as the response data of unknown measuring points. The working condition environment t is used as the test data, and the relationship between the response and the response is trained with p=14 groups, that is, the response of two channels in the nine channels is predicted, and the attached Figure 8 There are two channels in the response prediction results and the real results comparison results, attached Figure 9 It is the decibel difference graph between the predicted result and the real result. It can be seen that the response prediction result b...

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 present invention relates to an experimental apparatus for predicting the multi-point vibration response frequency domain under unknown load conditions, an experimental data generation method for predicting the multi-point vibration response frequency domain under unknown load conditions, and a method for predicting the vibration response of unknown measure points according the vibration response of the known measure points of the system by using the experimental apparatus and the experimental data under unrelated multi-source unknown load combined excitation. According to the vibration response prediction method, without the need to know or identify the transfer function, the load size and even the load position of the system, the support vector machine is directly used to train the relationship between the response data according to the historical experimental data. According to the technical scheme of the present invention, mainly for the environment of the working condition of unrelated multi-source unknown load combined excitation, the vibration response of the unknown measure points is predicted according the vibration response of the known measure points; the technical scheme of the present invention can solve the response prediction of the linear system and the nonlinear system; and the technical scheme of the present invention can solve the vibration response prediction situation of one unknown node and a plurality of unknown nodes.

Description

technical field [0001] The present invention relates to an experimental device for multi-point vibration response frequency domain prediction under unknown load conditions, a method for generating experimental data for multi-point vibration response frequency domain prediction under unknown load conditions, and using the experimental device and experimental data in unrelated A method of predicting the vibration response of unknown measuring points based on the support vector machine under the joint excitation of multi-source unknown loads based on the vibration responses of known measuring points of the system. Background technique [0002] With the development and progress of industry and control technology, the development of engineering structures in the fields of aerospace, ships, large machinery, bridges, etc. is becoming more and more complex, large-scale, and intelligent. Vibration is a design factor that has to be considered in mechanical design and navigation and ae...

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): G06F30/17G01M7/02
CPCG01M7/02G06F30/17
Inventor 王成詹威张忆文赖雄鸣何霆陈叶旺洪欣
Owner HUAQIAO UNIVERSITY
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