On-line fitting method of characteristic function of discrete control system based on data mining

A technology of decentralized control system and characteristic function, applied in general control system, control/regulation system, adaptive control and other directions, can solve the problems of fast calculation speed, difficult to accurately fit, and manual calculation of characteristic function.

Inactive Publication Date: 2009-09-02
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The calculation speed is fast and the fitting effect is good, which effectively solves the problem of manual calculation of the process characteristic function in the process industry and is difficult to accurately fit, and at the same time provides a practical method for on-line fitting of the characteristic function

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 fitting method of characteristic function of discrete control system based on data mining
  • On-line fitting method of characteristic function of discrete control system based on data mining
  • On-line fitting method of characteristic function of discrete control system based on data mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Below in conjunction with accompanying drawing, the implementation of the present invention will be further described, as Figure 1 to Figure 5 shown. Concrete implementation steps of the present invention are as follows:

[0052] Step 1. Obtain the relevant data to be fitted. The data scatter distribution is as follows: figure 2 , to perform necessary preprocessing on the data.

[0053] Step 2, establish the artificial neural network model, the structure is as follows figure 1 , use the data obtained in step 1 to fully train the neural network model, input X' into the trained neural network, calculate Y', denormalize Y', and get Y", and the obtained point set , i=1, 2, 3,..., n is the characteristic function curve, see image 3 .

[0054] Step 3: Perform broken-line fitting on the characteristic function curve obtained in step 2 to obtain the broken-line fitting result of the characteristic curve. The specific steps are:

[0055] ①Initialize, connect to the sta...

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 on-line fitting method of the characteristic function of a discrete control system based on data mining, and belongs to the technical field of industrial control. The on-line fitting method comprises: step one, obtaining relevant to-be-fitted data and carrying out preprocessing of the data; step two, establishing an artificial neural network model and calculating to obtain a characteristic function curve after training the model; step three, carrying out fold line fitting of the curve obtained in step two to obtain the fold line fitting result of the characteristic function; and step four, according to a new characteristic function curve, carrying out on-line correction of the fitting fold line of the current characteristic function, and ensuring that the correction method can meet the requirements of generating no disturbance during the operation of the discrete control system. The on-line fitting method combines an artificial intelligence method with a numerical calculation method, and has high calculation speed and ideal fitting effects; moreover, the method effectively solves the problems of the characteristic function of the prior discrete control system needs manual calculation and has difficult precise fitting and on-line correction.

Description

technical field [0001] The invention relates to a characteristic function fitting method, in particular to an online fitting method for a characteristic function of a distributed control system based on data mining, belonging to the technical field of industrial control. Background technique [0002] At present, the control devices of the process industry process mostly adopt the distributed control system. Due to the nonlinear characteristics of complex industrial processes usually exist. Therefore, it is generally necessary to modify this nonlinear characteristic with a function of a broken line in a distributed control system. At the same time, the online correction of the characteristic function cannot disturb the normal operation of the control system. Therefore, the broken line segment where the current working point is located must remain unchanged, and other broken line segments can be corrected online according to the new data. [0003] According to the literature...

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): G05B13/04
Inventor 叶敏忻建华叶春苏明孙漾
Owner SHANGHAI JIAO TONG 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