Title: Hybrid feature-driven learning system for abnormality detection and localization

Abstract

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.

Inventors:

Abbaszadeh, Masoud; D'Amato, Fernando Javier

Issue Date:

2021-10-12

Research Org.:

General Electric Co., Schenectady, NY (United States)

Sponsoring Org.:

USDOE

OSTI Identifier:

1859959

Patent Number(s):

11146579

Application Number:

16/138,408

Assignee:

General Electric Company (Schenectady, NY)

Patent Classifications (CPCs):

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

Show more

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

G06F17/18 - for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

G06N20/00 - Machine learning
G06N5/045 - {Explanation of inference steps}

H - ELECTRICITY H04 - ELECTRIC COMMUNICATION TECHNIQUE H04L - TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION

H04L43/16 - {using threshold monitoring}
H04L63/1425 - {Traffic logging, e.g. anomaly detection}
H04L63/145 - {the attack involving the propagation of malware through the network, e.g. viruses, trojans or worms}
H04L63/162 - {at the data link layer}
H04L63/20 - {for managing network security

H - ELECTRICITY H04 - ELECTRIC COMMUNICATION TECHNIQUE H04W - WIRELESS COMMUNICATION NETWORKS

H04W4/40 - for vehicles, e.g. vehicle-to-pedestrians [V2P]
H04W4/80 - Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication

Show less

DOE Contract Number:  

OE0000902

Resource Type:

Patent

Resource Relation:

Patent File Date: 09/21/2018

Country of Publication:

United States

Language:

English