Unlock instant, AI-driven research and patent intelligence for your innovation.

A Dynamic Process Monitoring Method Based on Distributed Extreme Learning Machine

An extreme learning machine, dynamic process technology, applied in program control, electrical program control, comprehensive factory control, etc., can solve problems such as large computing, disadvantageous online monitoring, etc., and achieve the effect of strong generalization ability

Active Publication Date: 2022-03-18
NINGBO UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when this idea based on kernel learning techniques implements online monitoring, it will involve a lot of calculations, which is not conducive to the implementation of online monitoring
Therefore, the research on nonlinear dynamic process monitoring needs to be further in-depth.

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 Dynamic Process Monitoring Method Based on Distributed Extreme Learning Machine
  • A Dynamic Process Monitoring Method Based on Distributed Extreme Learning Machine
  • A Dynamic Process Monitoring Method Based on Distributed Extreme Learning Machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The method of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0050] Such as figure 1 As shown, the present invention discloses a distributed fault monitoring method based on an extreme learning machine. The specific implementation manner of the method of the present invention will now be described in conjunction with a specific implementation case.

[0051] The tested process object is TE process, and the prototype of this process is an actual process flow in Eastman chemical production workshop. Currently, the TE process has been widely used in fault detection research as a standard experimental platform due to its complexity. The whole TE process includes 22 measured variables, 12 manipulated variables, and 19 component measured variables. The collected data are divided into 22 groups, including 1 group of data sets under normal working conditions and 21 groups of fault data. Among these fault data, 16 are ...

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 discloses a dynamic process monitoring method based on a distributed extreme learning machine, which aims to use ELM to establish a distributed nonlinear model for each measurement variable, so as to solve the fault detection problem in the nonlinear dynamic process. Specifically, the present invention uses each measurement variable as the output variable of ELM in turn, and other measurement variables and their delay measurement values ​​are used as input variables of ELM, so that the nonlinear dynamic relationship model between input and output can be established by using the ELM algorithm . When implementing fault detection, the estimation error of the distributed ELM model is used as the monitored object to implement fault detection. Compared with the traditional method, the method of the present invention establishes a distributed nonlinear model to give full play to the advantages of strong multi-model generalization ability, and describes the nonlinear input-output relationship between measurement variables one by one. Finally, the comparison of specific implementation cases proves that the method of the present invention is a more preferred nonlinear dynamic process monitoring method.

Description

technical field [0001] The invention relates to an industrial process monitoring method, in particular to a dynamic process monitoring method based on a distributed extreme learning machine. Background technique [0002] Under the trend of "big data" research and application, the large scale of modern industrial process objects and the high efficiency of production have put forward higher and higher requirements for real-time monitoring of process operation status, and data-driven process monitoring methods have become the most mainstream. implement technical means. It can be said that the timely detection of fault conditions during the operation of process objects is the only way to ensure product quality. The research on process monitoring technology with fault monitoring as the core task has been accompanied by the process of industrial development. Nowadays, due to the nonlinear characteristics of modern industrial process objects, the relationship between sampled data ...

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): G05B19/418
CPCG05B19/41875G05B19/41885Y02P90/02
Inventor 唐俊苗童楚东朱莹
Owner NINGBO UNIV