Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Nonlinear delay dynamic system model intelligent identification method

A dynamic system model, nonlinear dynamic technology, applied in general control systems, control/regulation systems, instruments, etc., can solve the problems of instability, fluctuations in the model switching process, and high complexity of local linear model identification

Active Publication Date: 2017-12-29
XIAN ESWIN MATERIAL TECH CO LTD +1
View PDF6 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 an intelligent identification method for a nonlinear time-delay dynamic system model, which solves the problem of high complexity in the identification of multiple local linear models in the existing nonlinear time-delay dynamic system identification method and the fluctuation and instability of the model switching process question

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
  • Nonlinear delay dynamic system model intelligent identification method
  • Nonlinear delay dynamic system model intelligent identification method
  • Nonlinear delay dynamic system model intelligent identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0173] nonlinear plant Among them, d=12, ω(k) is a white noise signal with a signal-to-noise ratio of 14.35. The input signal u(k) is a random signal with amplitude [-0.5,0.5].

[0174] In the identification experiment, the number of data is n=550, and the Gaussian function width factor is set as (max(u(k))-min(u(k))) / (2*n), where k∈[1,550]. When the input delay order gradually increases from 1 to 20, we get figure 2 Enter a plot of lag order versus root mean square error. It can be obtained from the figure that when the input time-delay order is 12, the root mean square error is the smallest. According to the nonlinear system output correlation time-delay determination algorithm, the time-delay order of the nonlinear controlled object is 12, which is consistent with the real system The time lags are the same, which shows the effectiveness of the algorithm for determining the time lag of the output correlation system. After the time delay of the nonlinear system is deter...

Embodiment 2

[0180] The silicon single crystal growth and preparation process is a nonlinear complex process coupled with multiple fields, in which there are nonlinear and large hysteresis characteristics between the thermal field temperature and the crystal diameter, so the silicon single crystal thermal field temperature-crystal diameter link is regarded as an identification process. Figure 5 The data of thermal field temperature and crystal diameter at a certain time during the growth process of a silicon single crystal with a diameter of 208mm were prepared for the TDR150 single crystal furnace, and the data sampling interval was 10s. Since the magnitudes of the silicon single crystal thermal field temperature and crystal diameter sampling data are inconsistent, the data were normalized to the range [-1,1] respectively.

[0181] In the thermal field temperature-crystal diameter system delay determination experiment, the Gaussian function width factor is set as the input range of the co...

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 discloses a nonlinear delay dynamic system model intelligent identification method. The method includes the following steps that: an NARX neural network model difference equation is assumed; nonlinear dynamic system delay in a set NARX neural network model is determined; the input and output order of a nonlinear dynamic system is determined; the number of hidden layer neurons of a three-layer single-output NARX neural network is determined; a three-layer NARX neural network model is determined; and finally, the validity of the three-layer NARX neural network model is verified, if the validity of the three-layer NARX neural network model is successfully verified, the method terminates, otherwise, the input and output order of the three-layer NARX neural network model is adjusted. With the method of the invention adopted, the problems of high complexity and instability which is caused by severe fluctuation of the switching process of a plurality of local linear identification methods of an existing nonlinear delay dynamic system identification method which adopts the plurality of local linear identification methods to perform identification can be solved.

Description

technical field [0001] The invention belongs to the technical field of nonlinear dynamic system identification methods, and in particular relates to a nonlinear time-delay dynamic system model identification method. Background technique [0002] Nonlinear time-delay dynamic systems are widely used in process control, model prediction and other fields. In these fields, sampling signals such as temperature, pressure, and flow of industrial sites are acquired and stored in real time by sensors. Based on a large amount of field sampling data, constructing a nonlinear dynamic model of an industrial process can improve the decision-making ability of the process. [0003] The traditional nonlinear time-delay dynamic system identification method usually obtains the time-delay of the system, and uses the local linearization method to obtain the local linear model of the controlled object or a certain working point in the production process. Although the local model is widely used i...

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): G05B13/02
CPCG05B13/0285
Inventor 刘丁段伟锋
Owner XIAN ESWIN MATERIAL TECH CO LTD
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
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