Gregory Kent Harrison

US Patent:

6741974, May 25, 2004

Filed:

Jun 2, 2000

Appl. No.:

09/586456

Inventors:

Gregory A. Harrison - Orlando FL
Keith Hollister - Orlando FL
Eric Worden - Orlando FL

Assignee:

Lockheed Martin Corporation - Orlando FL

International Classification:

G06F 1518

US Classification:

706 47, 706 13, 706 14

Abstract:

A system and a method enabling a software agent to learn about its environment, and learn how to perform jobs and tasks. Novel information is assimilated and used in an adaptive manner by the genetically evolving rule set of the agent. The agent learning system communicates with the external environment in an artificial economy through on-line auctions. Internal information also passes through message auctions, that provide chaining of rule execution. The agent continually attempts to automatically improve its performance with respect to fitness for a job.

US Patent:

7277823, Oct 2, 2007

Filed:

Sep 26, 2005

Appl. No.:

11/235440

Inventors:

Gregory A. Harrison - Oviedo FL, US
Alexey Turischev - Orlando FL, US

Assignee:

Lockheed Martin Corporation - Orlando FL

International Classification:

G06F 19/00

US Classification:

702183, 706 15

Abstract:

A neural network learns the operating modes of a system being monitored under normal operating conditions. Anomalies can be automatically detected and learned. A control command can be issued or an alert can be issued in response thereto.

US Patent:

7478013, Jan 13, 2009

Filed:

Aug 15, 2007

Appl. No.:

11/839350

Inventors:

Gregory A. Harrison - Oviedo FL, US
Alexey Turischev - Orlando FL, US

Assignee:

Lockheed Martin Corporation - Orlando FL

International Classification:

G06F 19/00

US Classification:

702183

Abstract:

A neural network learns the operating modes of a system being monitored under normal operating conditions. Anomalies can be automatically detected and learned. A control command can be issued or an alert can be issued in response thereto.

US Patent:

7917335, Mar 29, 2011

Filed:

Nov 18, 2008

Appl. No.:

12/272926

Inventors:

Gregory A. Harrison - Oviedo FL, US
Alexey Turischev - Orlando FL, US

Assignee:

Lockheed Martin Corporation - Orlando FL

International Classification:

G06F 17/00

US Classification:

702183

Abstract:

A neural network learns the operating modes of a system being monitored under normal operating conditions. Anomalies can be automatically detected and learned. A control command can be issued or an alert can be issued in response thereto.

US Patent:

8332337, Dec 11, 2012

Filed:

Oct 19, 2009

Appl. No.:

12/581402

Inventors:

Gregory A. Harrison - Oviedo FL, US
Michael A. Bodkin - Orlando FL, US
Michelle L. Harris - Oviedo FL, US
Stefan Herzog - Casselberry FL, US
Eric W. Worden - Orlando FL, US
Sreerupa Das - Ovideo FL, US
Richard Hall - Orlando FL, US

Assignee:

Lockheed Martin Corporation - Bethesda MD

International Classification:

G06E 1/00
G06E 3/00
G06F 15/18
G06G 7/00

US Classification:

706 20, 706 15, 706 16, 706 17, 706 18, 706 19, 706 21, 706 22, 700 1, 700 28, 700 29, 700 30, 700 31, 700 32, 700 33, 700 47, 700 48, 700 49, 700 50, 700104

Abstract:

Real-time condition-based analysis is performed on a machine for providing diagnostic and prognostic outputs indicative of machine status includes a signal processor for receiving signals from sensors adapted for measuring machine performance parameters. The signal processor conditions and shapes at least some of the received signals into an input form for a neural network. A fuzzy adaptive resonance theory neural network receives at least some of the conditioned and shaped signals, and detects and classifies a state of the machine based upon the received conditioned and shaped signals, and upon a predetermined ontology of machine states, diagnostics, and prognostics. The neural network can also determine from the machine state a health status thereof, which can comprise an anomaly, and output a signal representative of the determined health status. A Bayesian intelligence network receives the machine state from the neural network and determines a fault probability at a future time.

US Patent:

8407170, Mar 26, 2013

Filed:

Nov 25, 2009

Appl. No.:

12/625944

Inventors:

Gregory A. Harrison - Oviedo FL, US
Harold W. Nelson - San Diego CA, US
Ross Hall - Orlando FL, US
Lorie R. Ingraham - Orlando FL, US

Assignee:

Lockheed Martin Corporation - Orlando FL

International Classification:

G06F 17/00
G06N 5/00

US Classification:

706 45

Abstract:

A method for determining a root cause of a problem in a multiple-element system includes correlating an incoming alarm signal with an element x in a multiple-element system and accessing an implication list comprising a list of all elements upstream of element x. At least one element on the implication list is weighted with data relating to the at least one element. Taking into account the weighting step, a probability is calculated that an element on the implication list comprises a most-probable root cause of the subsequent alarm signal. The identified most-probable root cause of the incoming alarm signal is output.

US Patent:

8457942, Jun 4, 2013

Filed:

Oct 20, 2010

Appl. No.:

12/908597

Inventors:

Gregory A. Harrison - Oviedo FL, US
Salaheddine Saidi - St. Petersburg FL, US
Russell (Russ) Chan - Sunnyvale CA, US
Ann N. McCauslin - Aldie VA, US
Howard S. Kern - Silver Spring MD, US
Jeffrey S. Coffin - Germantown MD, US
David C. Benjamin - Orlando FL, US
Lawrence G. Elliott - Orlando FL, US
Christopher A. Young - Quincy MA, US
Stephen D. Peckham - Brighton MA, US
Michael D. Stewart - Wyncote PA, US
Mark E. Barbustiak - Atco NJ, US

Assignee:

Lockheed Martin Corporation - Orlando FL

International Classification:

G06F 17/50
G06G 7/62

US Classification:

703 13

Abstract:

Systems and methods for parallel, discrete, simulations include functional capabilities to incorporate one or more human operators or actors into the simulation process. Such individuals can be presented situations where one or more decisions are necessary with respect to ongoing events. Entered decisions are incorporated into simulated events and activities being simulated. These in turn influence the behavior of those entities and also initiate the occurrence of other time-based processes. An architecture artifact or product can be automatically created or updated by recording how a sequence of events took place. The creation of sections of the DoDAF OV-6C Operational Event Trace architectural diagram, for the executable architecture model, can be automatically performed to dynamically provide event traces in response to a live exercise.

US Patent:

8494981, Jul 23, 2013

Filed:

Jun 21, 2010

Appl. No.:

12/819574

Inventors:

Gregory A. Harrison - Oviedo FL, US
Thomas Wonneberger - Orlando FL, US
Jason Tr Smith - Orlando FL, US
David S. Maynard - Orlando FL, US
Eric W. Worden - Orlando FL, US

Assignee:

Lockheed Martin Corporation - Bethesda MD

International Classification:

G06F 15/18

US Classification:

706 12

Abstract:

A system, method, and computer-readable instructions for real-time characters with learning capabilities. A plurality of rules are defined in a rules-based system, each of the rules defining a condition that determines a behavior of a virtual agent when the rule is triggered by the condition being satisfied so that upon triggering of multiple rules at the same time, each of the behaviors of the multiple rules whose conditions were satisfied are combined into a resultant behavior for the virtual agent. This resultant behavior is compared with a desired behavior to providing feedback in the form of rewards or punishments to each of the multiple rules based on their corresponding contribution to the resultant behavior as compared to the desired behavior.