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

Rectification process quality monitoring service adaptive evolution method based on SVDD and Agent

A rectification process and quality monitoring technology, applied in chemical instruments and methods, separation methods, distillation adjustment/control, etc., can solve problems such as non-Gaussian data, achieve good monitoring results, make up for lack of initiative, save production costs and The effect of overhead

Active Publication Date: 2022-05-13
NANJING UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method uses the SVDD algorithm to monitor the abnormal data of the rectification process in time, effectively solving the problem of non-Gaussian and nonlinear monitoring of the actual rectification process data

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
  • Rectification process quality monitoring service adaptive evolution method based on SVDD and Agent
  • Rectification process quality monitoring service adaptive evolution method based on SVDD and Agent
  • Rectification process quality monitoring service adaptive evolution method based on SVDD and Agent

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] Refer to attached figure 1 , the present invention takes the business evolution of the distillation process quality monitoring software system caused by the change of the mass fraction of a certain ethanol distillation product as an example, and further describes its implementation and steps in detail.

[0075] Step 1: The 90% ethanol distillation process quality monitoring software system includes two parts, the front end and the back end.

[0076] S1. The front end is responsible for the input of distillation product quality information and data visualization. The DisID and Znm input boxes on the front end correspond to the back-end parameters one by one to ensure the uniqueness of the front-end and back-end requests. Click the "OK" button on the front end to pass the contents of the DisID and Znm input boxes ("C2H5OH" and 90) to the back end, and trigger the click event of the button. Inputting different distillation products or mass fractions is considered to be t...

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 rectification process quality monitoring self-adaptive evolution method based on SVDD and Agent, which can be used for updating and adjusting software of a rectification process quality monitoring system caused by the change of a rectification process manufacturing business, and solves the problem of self-adaptive evolution caused by the change of the manufacturing business. According to the method, all functional modules in a software system for monitoring the quality in the rectification process are packaged into Agents, and the Agents' internal parameters are dynamically updated by reading ECA evolution rules in combination with the characteristics of autonomy, environmental perception, initiative and the like of the Agents; the defects that an existing rectification process quality monitoring system does not have the self-learning ability and is difficult to autonomously deal with complex intelligent manufacturing business evolution are overcome. According to the method, the SVDD model algorithm is adopted to monitor the product quality in the rectification process in real time, and the monitoring problem of the actual rectification process under non-Gaussian and non-linear quality data can be effectively solved.

Description

technical field [0001] The invention belongs to the field of process industry intelligent manufacturing quality control technology and computer technology, and in particular provides an adaptive evolution method for distillation process quality monitoring business based on SVDD and Agent. Background technique [0002] Distillation is the most widely used separation operation unit in the process industry, and plays a pivotal role in the chemical separation process. Some scholars have proposed T 2 Traditional control charts such as , P, etc. monitor the quality of the rectification process. These control charts need to assume that the quality data of the rectification process satisfy the Gaussian distribution characteristics. However, the quality data of the actual distillation process has non-Gaussian and nonlinear characteristics, which leads to poor monitoring effect of the traditional control chart and more false alarms, which in turn affects the distillation production p...

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): G06Q10/06G06Q50/04G16C20/80G16C20/90G16C20/70G06K9/62B01D3/14B01D3/42
CPCG06Q10/06395G06Q50/04G16C20/80G16C20/90G16C20/70B01D3/14B01D3/42B01D3/4205B01D3/4227G06F18/24G06F18/214Y02P90/30
Inventor 张登峰张水波张泉灵
Owner NANJING UNIV OF TECH