US 12,260,304 B2
Staggered-sampling technique for detecting sensor anomalies in a dynamic univariate time-series signal
Neelesh Kumar Shukla, Madhapur (IN); Saurabh Thapliyal, Berkeley, CA (US); Matthew T. Gerdes, Oakland, CA (US); Guang C. Wang, San Diego, CA (US); and Kenny C. Gross, Escondido, CA (US)
Assigned to Oracle International Corporation, Redwood City, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Mar. 18, 2021, as Appl. No. 17/205,445.
Prior Publication US 2022/0300737 A1, Sep. 22, 2022
Int. Cl. G06N 20/00 (2019.01); G06F 18/21 (2023.01); G06N 5/04 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 18/217 (2023.01); G06N 5/04 (2013.01); G06F 2218/02 (2023.01); G06F 2218/18 (2023.01); G06F 2218/22 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method for detecting sensor anomalies in a univariate time-series signal, comprising:
during a surveillance mode, receiving the univariate time-series signal from a sensor in a monitored system;
performing a staggered-sampling operation on the univariate time-series signal to produce N sub-sampled time-series signals, wherein the staggered-sampling operation allocates consecutive samples from the univariate time-series signal to the N sub-sampled time-series signals in a round-robin ordering;
using a trained inferential model to generate estimated values for the N sub-sampled time-series signals based on cross-correlations with other signals in the N sub-sampled time-series signals;
performing an anomaly detection operation to detect incipient sensor anomalies in the univariate time-series signal based on differences between actual values and the estimated values for the N sub-sampled time-series signals; and
when an incipient sensor anomaly is detected, generating a notification.