DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Anomaly forecasting and early warning generation

Abstract

The example embodiments are directed to a system and method for forecasting anomalies in feature detection. In one example, the method includes storing feature behavior information of at least one monitoring node of an asset, including a normalcy boundary identifying normal feature behavior and abnormal feature behavior for the at least one monitoring node in feature space, receiving input signals from the at least one monitoring node of the asset and transforming the input signals into feature values in the feature space, wherein the feature values are located within the normalcy boundary, forecasting that a future feature value corresponding to a future input signal from the at least one monitoring node is going to be positioned outside the normalcy boundary based on the feature values within the normalcy boundary, and outputting information concerning the forecasted future feature value being outside the normalcy boundary for display.

Inventors:
;
Issue Date:
Research Org.:
General Electric Co., Schenectady, NY (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1986716
Patent Number(s):
11475124
Application Number:
15/594,779
Assignee:
General Electric Company (Schenectady, NY)
DOE Contract Number:  
OE0000833
Resource Type:
Patent
Resource Relation:
Patent File Date: 05/15/2017
Country of Publication:
United States
Language:
English

Citation Formats

Abbaszadeh, Masoud, and Mestha, Lalit Keshav. Anomaly forecasting and early warning generation. United States: N. p., 2022. Web.
Abbaszadeh, Masoud, & Mestha, Lalit Keshav. Anomaly forecasting and early warning generation. United States.
Abbaszadeh, Masoud, and Mestha, Lalit Keshav. Tue . "Anomaly forecasting and early warning generation". United States. https://www.osti.gov/servlets/purl/1986716.
@article{osti_1986716,
title = {Anomaly forecasting and early warning generation},
author = {Abbaszadeh, Masoud and Mestha, Lalit Keshav},
abstractNote = {The example embodiments are directed to a system and method for forecasting anomalies in feature detection. In one example, the method includes storing feature behavior information of at least one monitoring node of an asset, including a normalcy boundary identifying normal feature behavior and abnormal feature behavior for the at least one monitoring node in feature space, receiving input signals from the at least one monitoring node of the asset and transforming the input signals into feature values in the feature space, wherein the feature values are located within the normalcy boundary, forecasting that a future feature value corresponding to a future input signal from the at least one monitoring node is going to be positioned outside the normalcy boundary based on the feature values within the normalcy boundary, and outputting information concerning the forecasted future feature value being outside the normalcy boundary for display.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2022},
month = {10}
}

Works referenced in this record:

Cyber Security
patent-application, September 2016


Total Property Optimization System for Energy Efficiency and Smart Buildings
patent-application, June 2015


System and Method for Unsupervised Anomaly Detection on Industrial Time-Series Data
patent-application, October 2017


Industrial Dynamic Anomaly Detection Method and Apparatus
patent-application, October 2006


Software Defined Automation System and Architecture
patent-application, January 2018


Anomaly Detection Based on Performance Indicators
patent-application, August 2018


Risk Modeling System
patent-application, December 2016


Dynamic Prediction of Risk Levels for Manufacturing Operations Through Leading Risk Indicators
patent-application, March 2013


Anomaly Detection with K-Means Clustering and Artificial Outlier Injection
patent-application, May 2017


Patient Condition Display
patent-application, July 2004


Performance Testing Based on Variable Length Segmentation and Clustering of Time Series Data
patent-application, May 2017


Data-agnostic anomaly detection
patent-application, October 2014


Pre-Cognitive Security Information and Event Management
patent-application, February 2017


Communication Analysis Apparatus
patent-application, April 2004


Cyber-Attack Detection and Neutralization
patent-application, September 2018


Ultra-short-term wind power prediction and its application in early-warning system of power systems security and stability
conference, July 2011


Methods and Systems for the Industrial Internet of Things
patent-application, July 2018


Anomaly Detection Using Forecasting Methods ARIMA and HWDS
conference, November 2013

  • Pena, Eduardo H. M.; de Assis, Marcos V. O.; Proenca, Mario Lemes
  • 2013 32nd International Conference of the Chilean Computer Science Society (SCCC)
  • https://doi.org/10.1109/SCCC.2013.18

Tactical And Strategic Attack Detection And Prediction
patent-application, September 2007


Efficient detection of network anomalies
patent, May 2018


Vibration monitor and monitoring method
patent, December 1998


Methods and Apparatus
patent-application, November 2013


System to Detect Machine Initiated Events in Time Series Data
patent-application, June 2018