Dynamic process monitoring method based on bi-objective optimization algorithm

An optimization algorithm and dynamic process technology, applied in program control, electrical program control, comprehensive factory control, etc., can solve problems such as difficulty in obtaining accurate mechanism models and increasing complexity of production scale.

Active Publication Date: 2019-03-29
江苏酷猫企业服务有限公司
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Today, due to the large amount of data that can be measured and stored in modern industrial processes, and th

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
  • Dynamic process monitoring method based on bi-objective optimization algorithm
  • Dynamic process monitoring method based on bi-objective optimization algorithm
  • Dynamic process monitoring method based on bi-objective optimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The method of the present invention will be described in detail below in conjunction with the accompanying drawings and specific examples of implementation.

[0053] Such as figure 1 As shown, the invention discloses a dynamic process monitoring method based on a dual-objective optimization algorithm. The specific implementation of the inventive method is as follows:

[0054] Step (1): Collect samples under normal operating conditions of the production process to form a training data matrix X∈R n×m , and calculate the mean μ of each column vector in matrix X 1 , μ 2 ,…,μ m and the standard deviation δ 1 ,δ 2 ,…,δ m , corresponding to the composition mean vector μ=[μ 1 , μ 2 ,…,μ m ] T with standard deviation vector δ=[δ 1 ,δ 2 ,…,δ m ], where n is the number of training samples, m is the number of process measurement variables, R is the set of real numbers, R n×m Represents an n×m-dimensional real number matrix, and the superscript T represents the transp...

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 bi-objective optimization algorithm, which aims to decompose the autocorrelation feature components from data while considering two manifestations of autocorrelation. The method comprises the following steps: firstly converting two representations of autocorrelation into two optimal objective functions; then, solving the optimal projection transformation matrix by repeat iteration of two optimal targets; and finally, after separating the autocorrelation from the sample data, performing online monitoring on the error. The dynamic process monitoring method based on the bi-objective optimization algorithm has advantages that: the bi-objective optimization algorithm involved in the method of the invention is a completely new modeling algorithm, and considers two manifestations of the autocorrelation at the same time, which aims at separating the feature components of temporal autocorrelation. In addition, the dynamic process monitoring method based on the bi-objective optimization algorithm can eliminate the negative influence of the temporal autocorrelation by using the technique of error real-time monitoring afterseparating the autocorrelation from the sample data. And therefore, the method of the dynamic process monitoring method based on the bi-objective optimization algorithm is more suitable for dynamic process monitoring.

Description

technical field [0001] The invention relates to a data-driven process monitoring method, in particular to a dynamic process monitoring method based on a dual-objective optimization algorithm. Background technique [0002] Considering the importance of safe operation of the production process and stable product quality, academia and industry have invested a lot of manpower and material resources in the research of process monitoring methods with fault detection and diagnosis as the core task. At first, the fault detection and diagnosis method based on the mechanism model got more attention and application. Today, due to the large amount of data that can be measured and stored in modern industrial processes, and the complexity of production scale continues to expand, accurate mechanism models are often difficult to obtain. In this context, data-driven process monitoring research has been favored by many researchers and technicians. The basic idea of ​​the data-driven process...

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): G05B19/418
CPCG05B19/41885G05B2219/32339Y02P90/02
Inventor 来赟冬童楚东朱莹
Owner 江苏酷猫企业服务有限公司
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap