Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
PROCESS CONTROL METHOD AND SYSTEM WHICH USE HISTORY DATA-BASED NEURAL NETWORK LEARNING
Document Type and Number:
WIPO Patent Application WO/2019/066104
Kind Code:
A1
Abstract:
Provided are a process control method and system which use history data-based neural network learning. A process control method according to an embodiment of the present invention comprises: learning a control algorithm by using a past process variable and a past variable characteristic as an input and a past process control variable as an output; and using the learned control algorithm so as to receive a current process variable and a current variable characteristic, thereby outputting a current process control variable, wherein the variable characteristic is characteristic data extracted from the process variable. Therefore, automatic control can be performed by utilizing an artificial intelligence technology without stopping a process or an equipment operation.

Inventors:
JI YOUNG MIN (KR)
YOO JUNE JAE (KR)
Application Number:
PCT/KR2017/010922
Publication Date:
April 04, 2019
Filing Date:
September 29, 2017
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
KOREA ELECTRONICS TECHNOLOGY (KR)
International Classes:
G05B13/02; G05B11/36; G05B13/04; G05B19/418; G05B23/02
Foreign References:
JP03790129B
US20090312848A12009-12-17
KR20150014430A2015-02-06
JP2017087716A2017-05-25
KR101436057B12014-08-29
Attorney, Agent or Firm:
NAM, Choong Woo (KR)
Download PDF: