Update method for on-line detection data base

An update method and database technology, applied in electrical digital data processing, special data processing applications, instruments, etc., can solve the problems of poor prediction model stability, poor model adaptability, deviation rate, etc., to shorten the detection period and reduce hysteresis. Effect

Inactive Publication Date: 2012-07-11
MESNAC
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the update method of the detection database is basically carried out offline, so the current production condition information cannot be collected in time, and there is a certain deviation rate
[0005] 2. The screening update strategy of the existing detection database usually adopts the first-in-first-out queue update, that is, the information data that enters the database last replaces the initial information data, so it is easy to delete the most representative valid samples and keep them. Data samples with poor model fitness, the result is that the updated prediction model is less stable

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
  • Update method for on-line detection data base
  • Update method for on-line detection data base
  • Update method for on-line detection data base

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Example 1, such as figure 1 with figure 2 As shown, the online soft measurement method of rubber mixing Mooney viscosity is to take the first sample and detect it during the mixing process of the rubber material through banburying, extrusion, calendering, and kneading.

[0052] Specifically, the support vector machine function K(x i , x j )=i ), φ(x j )> to establish the Mooney viscosity prediction model;

[0053] On-line sampling operation is carried out after the mixed rubber material of the i-th car passes through the extrusion process and before the release agent;

[0054] For the first sample test of the rubber sample after sampling, the Mooney viscosity value is counted as x i ;

[0055] will x i Introduce the Mooney viscosity prediction model to predict the Mooney viscosity value Y of the i-th vehicle rubber sample detected by the conventional air-cooled parking process through the mapping relationship f: x→y i .

[0056] For the predicted Mooney viscos...

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 relates to an update method for on-line detection data base, which adopts on-line increasing update and a maximum deviation contribution screening strategy to achieve real-time optimization and data update of the on-line detection data base. The update method for the on-line detection data base includes: introducing at least nmin groups of Mooney viscosity values (xi, yi) to build a Mooney viscosity predicting module and construct a Moony viscosity on-line detection data base. When the Mooney viscosity value Y (wmin+1) predicted according to conventional air-cooled placing technology does not accord with the mixing craft quality standard, and predicted Mooney viscosity value y (wmin+1) accords with the mixing craft quality standard, the nmin groups of Mooney viscosity value (xi, yi) in the on-line detection data base are updated. The update method adopts the maximum deviation contribute screening strategy, the group of Mooney viscosity values corresponding to max (lambada i) (i=1, 2,..., nwmin+1) are deleted so as to rebuild a Moony viscosity predicting module.

Description

technical field [0001] The invention is suitable for rubber mixing Mooney viscosity detection process, in particular aims at the improvement of an online detection database updating method, and belongs to the field of rubber machinery and industrial automation control. Background technique [0002] With the continuous innovation of rubber material manufacturing technology, the mixed production of rubber materials with various formulations has been popularized and promoted. In order to improve the quality of the mixing process, the dispersion of additives and the overall uniformity of the rubber compound, it is necessary to carry out positioning sampling and inspection of the rubber compound of the designated train to judge the quality of the compound compound. As an important performance index to measure the viscosity characteristics, processability, and calendering characteristics of mixed rubber, Mooney viscosity has always been a key factor to improve the automation 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 Applications(China)
IPC IPC(8): G06F17/30G06Q10/00
Inventor 宋凯杭柏林杨殿才杜广华周宏斌李欣朱可辉孙培峰
Owner MESNAC
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