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

A multivariate data analysis method for dynamic system model verification

A dynamic system model and multivariate data technology, which is applied in the direction of electrical digital data processing, special data processing applications, character and pattern recognition, etc., can solve the problem of lack of nonlinear correlation between noise outputs of dynamic systems, achieve dimensionality reduction, and improve efficiency effect

Inactive Publication Date: 2018-12-28
CHONGQING UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, a few scholars have proposed verification methods for multivariate dynamic system simulation models. Most of these methods are aimed at the comprehensive measurement under the conflicting measurement results between the outputs of the multivariate dynamic system. They lack the dynamic system noise and the nonlinear correlation between the outputs. processing

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 multivariate data analysis method for dynamic system model verification
  • A multivariate data analysis method for dynamic system model verification
  • A multivariate data analysis method for dynamic system model verification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0043] Embodiments of the present invention provide a multivariate data analysis method for dynamic system model verification, such as figure 1 As shown, let T=[t 1 ,t 2 ,...,t m ] T and C=[c 1 ,c 2,...,c m ] T Represents a matrix of size n×m experimental and simulation data, a vector is the experimentally measured time series and the simulated time series of the i-th test point, and n is the length of the time series. Adopt the multivariate data analysis method that the present invention faces dynamic system model verification, comprise the following steps:

[0044] Step 1: Data noise reduction and normalization

[0045] In order to reduce or eliminate the influence of data noise factors on the model confirmation results, the wavelet packet denoising technology is introduced to decompose and reconstruct the original experimental...

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 relates to a multivariate data analysis method oriented to model verification of a multivariate dynamic system, belonging to the model verification field. The method comprises the following steps: 1, denoising and normalizing the original experiment data and simulation data through a wavelet packet denoising technology; 2, the normalized experimental data and simulation data being transformed from low-dimensional nonlinear space to high-dimensional linear space by a Gaussian kernel function; 3, dimensionality reduction of data in high-dimensional linear space; 4. error evaluationof dynamic response of each principal component, including phase error, amplitude error and shape error; 5, calculating the error scores of the phase, the amplitude and the shape, and calculating thecomprehensive scores of the principal components projected on the high-dimensional space experiment data and the simulation data aft the dimension reduction through the weight factors of the three kinds of errors; 6, determining the weighting factors of the comprehensive error score of each principal component to calculate the final score. The invention effectively processes the non-linear correlation between the data noise and each response of the system, and improves the data processing efficiency.

Description

technical field [0001] The invention belongs to the technical field of model verification, and relates to a multivariate data analysis method for dynamic system model verification. Background technique [0002] In digital product design, the simulation model used to replace the actual system is the basis and key of the entire product development process. The accuracy of the simulation model plays a decisive role in the digital design quality of the entire product model. However, since modeling and simulation are limited by various objective conditions and the information obtained may be incomplete, no matter how much time and money are spent on model establishment, the simulation model of a complex system is only an approximate replacement or finite approximation of the real system, without and A valid model of the real system that is absolutely identical. Therefore, model credibility assessment has gradually become an important issue concerned by scientific computing, sim...

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
IPC IPC(8): G06K9/62G06F17/50
CPCG06F30/20G06F18/2135
Inventor 詹振飞方宇东杨俊祺郑玲舒雅静
Owner CHONGQING 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