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

Learning Coefficient Control Device

A technology of learning coefficients and control devices, applied in adaptive control, general control systems, control/regulation systems, etc., can solve problems such as inability to learn, and achieve the effect of correcting model errors and improving accuracy

Active Publication Date: 2015-09-02
TOSHIBA MITSUBISHI-ELECTRIC IND SYST CORP
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In addition, the learning coefficient may also become an abnormal value due to the abnormal value of the actual value.
Since this is not an outlier due to the model, the outlier cannot be learned

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
  • Learning Coefficient Control Device
  • Learning Coefficient Control Device
  • Learning Coefficient Control Device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1 It is a structural diagram of applying the structure of the learning coefficient control apparatus of Example 1 to a tandem cold rolling mill. exist figure 1 Among them, the rolling mill adopts the following structure: that is, five stands from the first stand 1 to the fifth stand 5 are arranged in series. The rolled material 6 is rolled into a desired product in the direction of the arrow 7, and is coiled by a coiler not shown. Each rolling mill includes a device for measuring a rolling load (not shown) and the like. Furthermore, a plate thickness detection device 8 for measuring the plate thickness of the rolled material 6 is provided on the exit side of the fifth stand 5 .

[0050] The setting value of each actuator of the cold rolling mill is calculated so that a desired product can be obtained based on rolling information given in advance and using a rolling model. For example, by expressing the load model in Equation (2) and expressing the deformation...

Embodiment 2

[0125] Figure 6 It is a figure which applied the structure of the learning coefficient control apparatus of Example 2 to a tandem cold rolling mill. The learning coefficient control device of the second embodiment is also applicable to the same objects as the learning coefficient control device of the first embodiment.

[0126] The learning coefficient control device of the second embodiment differs from the learning coefficient control device of the first embodiment in that a correction value monitoring unit 24 and an operation display screen 25 (corresponding to the display unit) are additionally added. Hereinafter, only the configurations different from those of the learning coefficient control device of the first embodiment will be described.

[0127] The correction value monitoring unit 24 monitors whether the correction value calculated by the model correction value calculation unit 20 exceeds a preset limit value, and outputs an alarm to the operation display screen 2...

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 aims at providing a learning coefficient control device, even under the condition that a learning coefficient exceeds a limiting value, the learning coefficient control device is still capable of controlling the learning coefficient in the limiting value. A process model of a physical quantity is predicted based on more than two models, a learning calculation part (10) calculates a learning coefficient of each model based on the different between a predicted value and an actual value of the physical quantity, a transformation conversion calculation portion (14) calculates a conversion coefficient necessarily used for obtaining a adjusted value, the adjusted value is used for changing the predicted value of the other model, so as to keep the predicted value of the physical quantity finally obtained unchanged when the predicted value of a model is changed, a model adjusted value calculation part (20), under the condition that the learning coefficient of one model exceeds the first limiting value, based on a correction value of the learning coefficient from the model of a learning coefficient correction value calculation part (17) and an average value of the conversion efficient from a conversion coefficient average vale calculation part (19), calculates an adjusted value for a model used for compensating change amount of the predicted value generated by correction of the learning coefficient of a model by another model.

Description

technical field [0001] The present invention relates to a process of rolling metals, and more particularly to a learning coefficient control device for correcting parameters of a model representing the rolling process. Background technique [0002] Generally, in process control, a model representing a process phenomenon is generated, and a control system is constructed based on the model to implement control. Thus, the control accuracy of the final product has a lot to do with how well the model represents the process with high precision. Therefore, model learning is performed to compensate for process and model errors, in an effort to improve the accuracy of the model. [0003] P=Z P ·P ORI (1) [0004] In general, in order to improve the prediction accuracy of the rolling model, learning control is performed to compensate for the error between the actual rolling value and the predicted value of the rolling model. A typical rolling model is a load mo...

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): G05B13/04
Inventor 新居稔大手塚知幸下田直树
Owner TOSHIBA MITSUBISHI-ELECTRIC IND SYST CORP