Dynamic, resilient virtual sensing system and shadow controller for cyber-attack neutralization
Abstract
An industrial asset may have monitoring nodes (e.g., sensor or actuator nodes) that generate current monitoring node values. An abnormality detection and localization computer may receive the series of current monitoring node values and output an indication of at least one abnormal monitoring node that is currently being attacked or experiencing a fault. An actor-critic platform may tune a dynamic, resilient state estimator for a sensor node and output tuning parameters for a controller that improve operation of the industrial asset during the current attack or fault. The actor-critic platform may include, for example, a dynamic, resilient state estimator, an actor model, and a critic model. According to some embodiments, a value function of the critic model is updated for each action of the actor model and each action of the actor model is evaluated by the critic model to update a policy of the actor-critic platform.
- Inventors:
- Issue Date:
- Research Org.:
- General Electric Co., Schenectady, NY (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1986689
- Patent Number(s):
- 11468164
- Application Number:
- 16/710,051
- Assignee:
- General Electric Company (Schenectady, NY)
- DOE Contract Number:
- OE0000833
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 12/11/2019
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Roychowdhury, Subhrajit, Abbaszadeh, Masoud, and Dokucu, Mustafa Tekin. Dynamic, resilient virtual sensing system and shadow controller for cyber-attack neutralization. United States: N. p., 2022.
Web.
Roychowdhury, Subhrajit, Abbaszadeh, Masoud, & Dokucu, Mustafa Tekin. Dynamic, resilient virtual sensing system and shadow controller for cyber-attack neutralization. United States.
Roychowdhury, Subhrajit, Abbaszadeh, Masoud, and Dokucu, Mustafa Tekin. Tue .
"Dynamic, resilient virtual sensing system and shadow controller for cyber-attack neutralization". United States. https://www.osti.gov/servlets/purl/1986689.
@article{osti_1986689,
title = {Dynamic, resilient virtual sensing system and shadow controller for cyber-attack neutralization},
author = {Roychowdhury, Subhrajit and Abbaszadeh, Masoud and Dokucu, Mustafa Tekin},
abstractNote = {An industrial asset may have monitoring nodes (e.g., sensor or actuator nodes) that generate current monitoring node values. An abnormality detection and localization computer may receive the series of current monitoring node values and output an indication of at least one abnormal monitoring node that is currently being attacked or experiencing a fault. An actor-critic platform may tune a dynamic, resilient state estimator for a sensor node and output tuning parameters for a controller that improve operation of the industrial asset during the current attack or fault. The actor-critic platform may include, for example, a dynamic, resilient state estimator, an actor model, and a critic model. According to some embodiments, a value function of the critic model is updated for each action of the actor model and each action of the actor model is evaluated by the critic model to update a policy of the actor-critic platform.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2022},
month = {10}
}
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Autonomous Reconfigurable Virtual Sensing System for Cyber-Attack Neutralization
patent-application, July 2019
- Abbaszadeh, Masoud; Mestha, Lalit Keshav
- US Patent Application 15/977,595; 2019/0230106 Al
Resilient state estimation against switching attacks on stochastic cyber-physical systems
conference, December 2015
- Yong, Sze Zheng; Zhu, Minghui; Frazzoli, Emilio
- 2015 54th IEEE Conference on Decision and Control (CDC)
Dynamic Concurrent Learning Method to Neutralize Cyber Attacks and Faults for Industrial Asset Monitoring Nodes
patent-application, July 2019
- Mestha, Lalit Keshav; Anubl, Olugbenga; Achanta, hema
- US Patent Application 15/986,996; 2019/0230119 Al
Method for Active Fault Tolerant Control of Turbofan Engine Control System
patent-application, May 2021
- Ding, Nan; Ma, Yanhua; Gao, Yanlei
- US Patent Application 16/770801; 20210156314
Resilient control design for distributed cyber-physical systems
patent, April 2018
- Ji, Kun
- US Patent Document 9,942,245
Using virtual sensors to accommodate industrial asset control systems during cyber attacks
patent-application, February 2019
- Mestha, Lalit Keshav; Achanta, Hema Kumari; John, Justin Varkey
- US Patent Application 15/683250; 20190068618
Fault Isolation Using On-Board Diagnostic (OBD) Capability Data
patent-application, June 2022
- Abraham, Jeffrey Diwakar; Schmalz De Bernardi, Marcela; Brahma, Avra
- US Patent Application 17/247383; 20220180673
Hierarchical fault prediction, detection and localization in PV systems with distributed electronics
patent, January 2017
- Batten, Robert; Naiknaware, Ravindranath
- US Patent Document 9,547,033
Cyberattack-Resilient Control System Design
patent-application, July 2019
- Wei, Dong; Wang, Lingyun; de Agular, Leandro Pfleger
- US Patent Application 16/331,159; 2019/0220374 Al
Control tower and enterprise management platform with trainable expert agents for value chain networks
patent-application, November 2021
- Cella, Charles Howard; Spitz, Richard; Cardno, Andrew
- US Patent Application 17/333275; 20210357850
Virtual Sensor Supervised Learning for Cyber-Attack Neutralization
patent-application, April 2021
- Roychowdhury, Subhrajit; Abbaszadeh, Masoud; Dokucu, Mustafa Tekin
- US Patent Application 16/666,807; 2021/0126943 Al
Dynamic, Resilient Sensing System for Automatic Cyber-Attack Neutralization
patent-application, April 2021
- Dokucu, Mustafa Tekin; Roychowdhury, Subhrajit; Anubi, Olugbenga
- US Patent Application 16/654319; 20210120031
Virtual to Real Reinforcement Learning for Autonomous Driving
conference, January 2017
- Pan, Xinlei; You, Yurong; Wang, Ziyan
- Procedings of the British Machine Vision Conference 2017
Adversarial attack and defense in reinforcement learning-from AI security view
journal, March 2019
- Chen, Tong; Liu, Jiqiang; Xiang, Yingxiao
- Cybersecurity, Vol. 2, Issue 1