Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Hybrid feature-driven learning system for abnormality detection and localization

Patent ·
OSTI ID:1859959
A cyber-physical system may have a plurality of monitoring nodes each generating a series of current monitoring node values over time representing current operation of the system. A data-driven features extraction computer platform may receive the series of current monitoring node values and generate current data-driven feature vectors based on the series of current monitoring node values. A residual features extraction computer platform may receive the series of current monitoring node values, execute a system model and utilize a stochastic filter to determine current residual values, and generate current residual-driven feature vectors based on the current residual values. An abnormal detection platform may then receive the current data-driven and residual-driven feature vectors and compare the current data-driven and residual-driven feature vectors with at least one decision boundary associated with an abnormal detection model. An abnormal alert signal may then be transmitted when appropriate based on a result of said comparison.
Research Organization:
General Electric Co., Schenectady, NY (United States)
Sponsoring Organization:
USDOE
DOE Contract Number:
OE0000902
Assignee:
General Electric Company (Schenectady, NY)
Patent Number(s):
11,146,579
Application Number:
16/138,408
OSTI ID:
1859959
Country of Publication:
United States
Language:
English

References (1)

Attack Detection and Identification in Cyber-Physical Systems journal November 2013