On-line evaluation method of industrial process operation status based on the idea of ​​just-in-time learning

A technology of industrial process and operating status, applied in the direction of program control, comprehensive factory control, electrical program control, etc., can solve problems such as difficulty in establishing a high-precision evaluation model, and achieve the effect of high evaluation accuracy

Active Publication Date: 2021-06-25
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the traditional real-time learning method, sample selection and model building are carried out separately, especially when the sample size is insufficient, the selected samples may not be suitable for model building, and it is difficult to establish a high-precision evaluation model

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
  • On-line evaluation method of industrial process operation status based on the idea of ​​just-in-time learning
  • On-line evaluation method of industrial process operation status based on the idea of ​​just-in-time learning
  • On-line evaluation method of industrial process operation status based on the idea of ​​just-in-time learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0069] figure 1 It is a flow chart of the online evaluation method of industrial process operation state based on the idea of ​​instant learning in the present invention, specifically comprising the following steps:

[0070] (1) Acquisition of data to be analyzed: obtain J measured variables in a dynamic industrial process, measure each measured variable once, and obtain the data of the dynamic process x ji Form a two-dimensional data matrix X (J×I), x ji express X The element in row j and column i in .

[0071] (2) Data matrix X Standardization of: Yes x ji After subtracting the mean value and dividing by the standard deviation, the matrix X(J×I) with the mean value of each column being 0 and the variance being 1 is obtained. The calculation formula is as follows:

[0072]

[0073] where x ji Represents the elements of the jth ro...

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 an online evaluation method for the operation state of an industrial process based on the idea of ​​instant learning. The method aims at the evaluation problem of the operation state of the industrial process with dynamic changes in process characteristics and a small amount of modeling data; firstly, according to the online test data, a modeling The optimization objective of the data selection part; then, establish the optimization objective of the state evaluation part; use the evolutionary optimization algorithm to solve the objective function, and obtain the modeling data and evaluation model at the same time; finally, use the established evaluation model and Bayesian posterior probability The evaluation index is used to obtain the evaluation results of the operating status. The invention considers the establishment of modeling data and evaluation model at the same time, and simultaneously solves two parts of optimization objectives in order to obtain the global optimal solution. The present invention improves the accuracy of operating state evaluation by means of more refined modeling, and can finally be applied to actual industrial production sites to ensure high-efficiency and economical operation of industrial processes with dynamic changes and small amount of modeling data.

Description

technical field [0001] The invention belongs to the field of online evaluation of the operation status of industrial processes, and in particular relates to an online evaluation method of the operation status of industrial processes based on the idea of ​​instant learning. Background technique [0002] In order to obtain higher comprehensive economic benefits of enterprises, the optimal evaluation of industrial production process operation status, as a new research topic, has gradually attracted the attention of academia and industry in recent years. Different from the process monitoring problem for the purpose of distinguishing between "normal" and "faulty" process operation, the evaluation of the superiority of the process operation status refers to further judging the pros and cons of the process operation status on the basis of the normal operation of the process, which is helpful for enterprise management Operators and production operators can grasp the operation level ...

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
CPCG05B19/41885G05B2219/32339Y02P90/02
Inventor 邹筱瑜潘杰
Owner ZHEJIANG UNIV
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