US 12,235,635 B2
Method for setting model threshold of facility monitoring system
Donghwan Kim, Seoul (KR); Daeyoung Kim, Seoul (KR); Hyuk Jun Na, Seoul (KR); Kyoung Shik Jun, Seoul (KR); and Woonkyu Choi, Seoul (KR)
Assigned to AIDENTYX, INC., Austin, TX (US)
Filed by Aidentyx, Inc., Austin, TX (US)
Filed on Apr. 11, 2023, as Appl. No. 18/298,939.
Application 18/298,939 is a continuation of application No. 17/136,391, filed on Dec. 29, 2020, granted, now 11,662,718.
Claims priority of application No. 10-2020-0164006 (KR), filed on Nov. 30, 2020.
Prior Publication US 2023/0244221 A1, Aug. 3, 2023
Int. Cl. G06N 20/00 (2019.01); G05B 19/418 (2006.01); G05B 23/02 (2006.01); G06F 18/214 (2023.01); G06N 3/08 (2023.01); G06F 8/61 (2018.01); G06N 3/088 (2023.01)
CPC G05B 23/0235 (2013.01) [G05B 19/4183 (2013.01); G05B 19/4185 (2013.01); G05B 19/41885 (2013.01); G06F 18/214 (2023.01); G06N 3/08 (2013.01); G06F 8/61 (2013.01); G06N 3/088 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method of setting a model threshold value for detecting an anomaly of a facility monitoring system, the method comprising:
acquiring sensor data output from each sensor;
extracting two or more feature values for each of variables included in the sensor data of each sensor, wherein the two or more feature values for each of the variables comprises an upper control limit value and a lower control limit value;
acquiring output data by inputting input data to a trained neural network model to generate the output data, wherein the input data consists of a combination of the extracted feature value; and
comparing the input data and the output data to generate a calculated comparison result value, and determining a threshold value which is for detecting an anomaly, based on the calculated comparison result value;
updating the threshold value based on (i) a past threshold value of the trained neural network model corresponding to a past failure class, (ii) a past median value of device state indexes corresponding to a normal section, (iii) a current threshold value of the trained neural network model corresponding to a current failure class, (iv) a current median value of device state indexes corresponding to a normal section, and (v) a correction value for failure cost, when the current failure class corresponds to the past failure class.