Title:
OPERATION PREDICTION SYSTEM, METHOD, AND COMPUTER PROGRAM USING SIGNAL GROUP-BASED LEARNING MODEL OF INDUSTRIAL PLANT FACILITY
Document Type and Number:
WIPO Patent Application WO/2020/246662
Kind Code:
A1
Abstract:
An operation prediction method using a signal group-based learning model of an industrial plant facility according to an embodiment of the present invention may comprise the steps of: (A) classifying industrial plant facilities according to a facility standard and identifying signals in the classified facilities, so as to define a signal according to a facility; (B) extracting a signal of an interval in which an industrial plant facility has performed a normal operation, and generating raw data; (C) calculating correlation coefficients with respect to signals of each facility group, and generating groups according to classified correlation coefficient values; (D) generating representative data of signals in each group, calculating a correlation coefficient with respect to the representative data between groups, and configuring a correlation between the groups according to the correlation coefficient; (E) performing data learning for a normal operation interval for each group and implementing a learning model; and (F) calculating prediction values of plant facilities for each operation mode by using the learning model for the normal operation interval.
Inventors:
CHO MAN YOUNG (KR)
Application Number:
PCT/KR2019/013663
Publication Date:
December 10, 2020
Filing Date:
October 17, 2019
Export Citation:
Assignee:
GAONPLATFORM INC (KR)
International Classes:
G05B23/02; G06N5/04; G06N20/00
Domestic Patent References:
| WO2015030417A1 | 2015-03-05 |
Foreign References:
| KR20110116378A | 2011-10-26 | |||
| KR20180024331A | 2018-03-08 | |||
| KR100997009B1 | 2010-11-25 | |||
| JP2018024055A | 2018-02-15 |
Attorney, Agent or Firm:
OAM PATENT & TRADEMARK LAW FIRM (KR)
Download PDF: