US 12,282,308 B2
Intelligent process anomaly detection and trend projection system
Aldimir Lyubchev Mihnev, Lake Forest, CA (US); Prarthana Rohitkumar Shah, Lake Forest, CA (US); Brian Kenneth Erickson, Lake Forest, CA (US); and William Charles Winn Bielke, Lake Forest, CA (US)
Assigned to Aveva Software, LLC, Lake Forest, CA (US)
Filed by AVEVA Software, LLC, Lake Forest, CA (US)
Filed on Sep. 15, 2020, as Appl. No. 17/021,654.
Claims priority of provisional application 62/901,080, filed on Sep. 16, 2019.
Prior Publication US 2021/0080928 A1, Mar. 18, 2021
Int. Cl. G05B 19/4063 (2006.01); G06N 3/08 (2023.01)
CPC G05B 19/4063 (2013.01) [G06N 3/08 (2013.01); G05B 2219/31449 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A system for providing an anomaly detection and trend projection of industrial asset deterioration comprising:
one or more computers comprising one or more processors and one or more non-transitory computer readable media, the one or more non-transitory computer readable media including instructions stored thereon that when executed by the one or more processors implement the following steps:
receiving a signal from a sensor coupled to an asset within an industrial process, the asset comprising of a plurality of components;
determining if at least one of the plurality of components is a seasonal component that predictably degrades during regular intervals, by analyzing the signal for a variation in a trend that occurs within the signal at the regular intervals during a lifespan of the asset;
identifying a degradation part of the signal and a normal part of the signal in response to a determination that the seasonal component was not detected within the plurality of components of the asset;
separating the degradation part of the signal from the normal part of the signal;
identifying one or more patterns of a degradation part of the signal and the normal part of the signal;
determining a prediction of a future development of an anomaly based on the one or more patterns;
determining an estimate of remaining useful life for the asset based on the prediction of the future development of the anomaly and the one or more patterns; and
performing a maintenance procedure on at least one of the components of the asset based on the estimate of remaining useful life.