Data-driven model construction for industrial asset decision boundary classification

Abbaszadeh, Masoud; Mestha, Lalit Keshav; Bushey, Cody Joe

Title: Data-driven model construction for industrial asset decision boundary classification

Abstract

In some embodiments, a system model construction platform may receive, from a system node data store, system node data associated with an industrial asset. The system model construction platform may automatically construct a data-driven, dynamic system model for the industrial asset based on the received system node data. A synthetic attack platform may then inject at least one synthetic attack into the data-driven, dynamic system model to create, for each of a plurality of monitoring nodes, a series of synthetic attack monitoring node values over time that represent simulated attacked operation of the industrial asset. The synthetic attack platform may store, in a synthetic attack space data source, the series of synthetic attack monitoring node values over time that represent simulated attacked operation of the industrial asset. This information may then be used, for example, along with normal operational data to construct a threat detection model for the industrial asset.

Inventors:: Abbaszadeh, Masoud; Mestha, Lalit Keshav; Bushey, Cody Joe

Issue Date:: 2020-06-02

Research Org.:: General Electric Co., Schenectady, NY (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1650970

Patent Number(s):: 10671060

Application Number:: 15/681,974

Assignee:: General Electric Company (Schenectady, NY)

Patent Classifications (CPCs):: G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL

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

Show more

G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL
G05B17/02 - electric
G05B19/41885 - {characterised by modeling, simulation of the manufacturing system}
G05B2219/35269 - Checking data, parity, diagnostic
G05B2219/36546 - Memory protection, protected fields

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F21/55 - Detecting local intrusion or implementing counter-measures
G06F21/566 - {Dynamic detection, i.e. detection performed at run-time, e.g. emulation, suspicious activities}
G06F21/604 - {Tools and structures for managing or administering access control systems}
G06F2221/034 - Test or assess a computer or a system

H - ELECTRICITY H04 - ELECTRIC COMMUNICATION TECHNIQUE H04L - TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
H04L63/1408 - {by monitoring network traffic
H04L63/1433 - {Vulnerability analysis}

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y04 - INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS Y04S - SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
Y04S40/20 - Information technology specific aspects

Show less

DOE Contract Number:: OE0000833

Resource Type:: Patent

Resource Relation:: Patent File Date: 08/21/2017

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Abbaszadeh, Masoud, Mestha, Lalit Keshav, and Bushey, Cody Joe. Data-driven model construction for industrial asset decision boundary classification.  United States: N. p., 2020. 
        Web.

Copy to clipboard


                    Abbaszadeh, Masoud, Mestha, Lalit Keshav, & Bushey, Cody Joe. Data-driven model construction for industrial asset decision boundary classification.  United States.

Copy to clipboard


                    Abbaszadeh, Masoud, Mestha, Lalit Keshav, and Bushey, Cody Joe. Tue .  
        "Data-driven model construction for industrial asset decision boundary classification".  United States.  https://www.osti.gov/servlets/purl/1650970.

Copy to clipboard


                    
@article{osti_1650970,

  title        = {Data-driven model construction for industrial asset decision boundary classification},

  author       = {Abbaszadeh, Masoud and Mestha, Lalit Keshav and Bushey, Cody Joe},

  abstractNote = {In some embodiments, a system model construction platform may receive, from a system node data store, system node data associated with an industrial asset. The system model construction platform may automatically construct a data-driven, dynamic system model for the industrial asset based on the received system node data. A synthetic attack platform may then inject at least one synthetic attack into the data-driven, dynamic system model to create, for each of a plurality of monitoring nodes, a series of synthetic attack monitoring node values over time that represent simulated attacked operation of the industrial asset. The synthetic attack platform may store, in a synthetic attack space data source, the series of synthetic attack monitoring node values over time that represent simulated attacked operation of the industrial asset. This information may then be used, for example, along with normal operational data to construct a threat detection model for the industrial asset.},

  doi          = {},

  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2020},

  month        = {6}

}

Copy to clipboard

Patent:

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Method for Quantitative Resilience Estimation of Industrial Control Systems
patent-application, May 2013

Wei, Dong; Ji, Kun
US Patent Application 13/703158; 20130132149
URL: https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/20130132149

Method to indentify anomalous data using cascaded K-Means clustering and an ID3 decision tree
patent, September 2010

Phoha, Vir V.; Balagani, Kiran S.
US Patent Document 7,792,770
URL: https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/7792770

System For Securing Electric Power Grid Operations From Cyber-Attack
patent-application, October 2015

Gooding, Jeff; McDonald, Jeremy
US Patent Application 14/228730; 20150281278
URL: https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/20150281278

Similar Records in DOE Patents and OSTI.GOV collections:

Multi-class decision system for categorizing industrial asset attack and fault types

Patent Abbaszadeh, Masoud; Mestha, Lalit Keshav; Yan, Weizhong

According to some embodiments, a plurality of monitoring nodes may each generate a series of current monitoring node values over time that represent a current operation of the industrial asset. A node classifier computer, coupled to the plurality of monitoring nodes, may receive the series of current monitoring node values and generate a set of current feature vectors. The node classifier computer may also access at least one multi-class classifier model having at least one decision boundary. The at least one multi-class classifier model may be executed and the system may transmit a classification result based on the set ofmore » « less
Full Text Available
System for conversion between the boundary representation model and a constructive solid geometry model of an object

Patent Christensen, Noel C [Kansas City, MO]; Emery, James D [Kansas City, MO]; Smith, Maurice L [Kansas City, MO]

A system converts from the boundary representation of an object to the constructive solid geometry representation thereof. The system converts the boundary representation of the object into elemental atomic geometrical units or I-bodies which are in the shape of stock primitives or regularized intersections of stock primitives. These elemental atomic geometrical units are then represented in symbolic form. The symbolic representations of the elemental atomic geometrical units are then assembled heuristically to form a constructive solid geometry representation of the object usable for manufacturing thereof. Artificial intelligence is used to determine the best constructive solid geometry representation from the boundarymore » « less
Full Text Available
Using virtual sensors to accommodate industrial asset control systems during cyber attacks

Patent Mestha, Lalit Keshav; Achanta, Hema Kumari; John, Justin Varkey; ...

In some embodiments, an industrial asset may be associated with a plurality of monitoring nodes, each monitoring node generating a series of monitoring node values over time that represent operation of the industrial asset. A threat detection computer may determine that an attacked monitoring node is currently being attacked. Responsive to this determination, a virtual sensor coupled to the plurality of monitoring nodes may estimate a series of virtual node values for the attacked monitoring node(s) based on information received from monitoring nodes that are not currently being attacked. The virtual sensor may then replace the series of monitoring nodemore » « less
Full Text Available
Using virtual sensors to accommodate industrial asset control systems during cyber attacks

Patent Mestha, Lalit Keshav; Achanta, Hema Kumari; John, Justin Varkey; ...

In some embodiments, an industrial asset may be associated with a plurality of monitoring nodes, each monitoring node generating a series of monitoring node values over time that represent operation of the industrial asset. A threat detection computer may determine that an attacked monitoring node is currently being attacked. Responsive to this determination, a virtual sensor coupled to the plurality of monitoring nodes may estimate a series of virtual node values for the attacked monitoring node(s) based on information received from monitoring nodes that are not currently being attacked. The virtual sensor may then replace the series of monitoring nodemore » « less
Full Text Available
Dynamic concurrent learning method to neutralize cyber attacks and faults for industrial asset monitoring nodes

Patent Mestha, Lalit Keshav; Anubi, Olugbenga; Achanta, Hema Kumari

Input signals may be received from monitoring nodes of the industrial asset, each input signal comprising time series data representing current operation. A neutralization engine may transform the input signals into feature vectors in feature space, each feature vector being associated with one of a plurality of overlapping batches of received input signals. A dynamic decision boundary may be generated based on the set of feature vectors, and an abnormal state of the asset may be detected based on the set of feature vectors and a predetermined static decision boundary. An estimated neutralized value for each abnormal feature value maymore » « less
Full Text Available

Similar Records

Title: Data-driven model construction for industrial asset decision boundary classification

Abstract

Citation Formats

Method for Quantitative Resilience Estimation of Industrial Control Systems patent-application, May 2013

Method to indentify anomalous data using cascaded K-Means clustering and an ID3 decision tree patent, September 2010

System For Securing Electric Power Grid Operations From Cyber-Attack patent-application, October 2015

Method for Quantitative Resilience Estimation of Industrial Control Systems
patent-application, May 2013

Method to indentify anomalous data using cascaded K-Means clustering and an ID3 decision tree
patent, September 2010

System For Securing Electric Power Grid Operations From Cyber-Attack
patent-application, October 2015