Adaptive model training system and method

Bickford, Randall L; Palnitkar, Rahul M

Title: Adaptive model training system and method

Abstract

An adaptive model training system and method for filtering asset operating data values acquired from a monitored asset for selectively choosing asset operating data values that meet at least one predefined criterion of good data quality while rejecting asset operating data values that fail to meet at least the one predefined criterion of good data quality; and recalibrating a previously trained or calibrated model having a learned scope of normal operation of the asset by utilizing the asset operating data values that meet at least the one predefined criterion of good data quality for adjusting the learned scope of normal operation of the asset for defining a recalibrated model having the adjusted learned scope of normal operation of the asset.

Inventors:: Bickford, Randall L; Palnitkar, Rahul M

Issue Date:: 2014-11-18

Research Org.:: Intellectual Assets LLC, Lake Tahoe, NV (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1163977

Patent Number(s):: 8892478

Application Number:: 13/803,436

Assignee:: Intellectual Assets LLC (Lake Tahoe, NV)

Patent Classifications (CPCs):: G - PHYSICS G01 - MEASURING G01N - INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES

G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL

Show more

G - PHYSICS G01 - MEASURING G01N - INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
G01N21/274 - {Calibration, base line adjustment, drift correction}

G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL
G05B23/0235 - {based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G06N20/00 - Machine learning
G06N5/02 - Knowledge representation
G06N3/004 - {Artificial life, i.e. computers simulating life}

G - PHYSICS G06 - COMPUTING G06Q - DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES
G06Q50/06 - Electricity, gas or water supply

G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL
G05B13/02 - electric

G - PHYSICS G01 - MEASURING G01R - MEASURING ELECTRIC VARIABLES
G01R35/005 - {Calibrating

H - ELECTRICITY H02 - GENERATION H02J - CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER
H02J3/00 - Circuit arrangements for ac mains or ac distribution networks

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G06N5/04 - Inference methods or devices

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F17/10 - Complex mathematical operations {

G - PHYSICS G01 - MEASURING G01K - MEASURING TEMPERATURE
G01K15/005 - {Calibration}

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G06N3/08 - Learning methods

Show less

DOE Contract Number:: FG02-04ER83949

Resource Type:: Patent

Resource Relation:: Patent File Date: 2013 Mar 14

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Bickford, Randall L, and Palnitkar, Rahul M. Adaptive model training system and method.  United States: N. p., 2014. 
        Web.

Copy to clipboard


                    Bickford, Randall L, & Palnitkar, Rahul M. Adaptive model training system and method.  United States.

Copy to clipboard


                    Bickford, Randall L, and Palnitkar, Rahul M. Tue .  
        "Adaptive model training system and method".  United States.  https://www.osti.gov/servlets/purl/1163977.

Copy to clipboard


                    
@article{osti_1163977,

  title        = {Adaptive model training system and method},

  author       = {Bickford, Randall L and Palnitkar, Rahul M},

  abstractNote = {An adaptive model training system and method for filtering asset operating data values acquired from a monitored asset for selectively choosing asset operating data values that meet at least one predefined criterion of good data quality while rejecting asset operating data values that fail to meet at least the one predefined criterion of good data quality; and recalibrating a previously trained or calibrated model having a learned scope of normal operation of the asset by utilizing the asset operating data values that meet at least the one predefined criterion of good data quality for adjusting the learned scope of normal operation of the asset for defining a recalibrated model having the adjusted learned scope of normal operation of the asset.},

  doi          = {},

  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2014},

  month        = {11}

}

Copy to clipboard

Patent:

View Patent

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Generating an Interpretable Family of Fuzzy Partitions From Data
journal, June 2004

Guillaume, S.; Charnomordic, B.
IEEE Transactions on Fuzzy Systems, Vol. 12, Issue 3
https://doi.org/10.1109/TFUZZ.2004.825979

Real-time sensor validation for propulsion systems
conference, February 2013

Bickford, R.; Bickmore, T.; Meyer, C.
AIAA Defense and Civil Space Programs Conference and Exhibit
https://doi.org/10.2514/6.1998-5184

A turbine engine real-time test data validation and analysis system, generation 1.0
conference, February 2013

Kelly, Paul; Holt, Lanny
36th AIAA/ASME/SAE/ASEE Joint Propulsion Conference and Exhibit
https://doi.org/10.2514/6.2000-3626

Similar Records in DOE Patents and OSTI.GOV collections:

Adaptive model training system and method

Patent Bickford, Randall L; Palnitkar, Rahul M; Lee, Vo

An adaptive model training system and method for filtering asset operating data values acquired from a monitored asset for selectively choosing asset operating data values that meet at least one predefined criterion of good data quality while rejecting asset operating data values that fail to meet at least the one predefined criterion of good data quality; and recalibrating a previously trained or calibrated model having a learned scope of normal operation of the asset by utilizing the asset operating data values that meet at least the one predefined criterion of good data quality for adjusting the learned scope of normalmore »« less
Full Text Available
Method and system for determining the torque required to launch a vehicle having a hybrid drive-train

Patent Hughes, Douglas A.

A method and system are provided for determining the torque required to launch a vehicle having a hybrid drive-train that includes at least two independently operable prime movers. The method includes the steps of determining the value of at least one control parameter indicative of a vehicle operating condition, determining the torque required to launch the vehicle from the at least one determined control parameter, comparing the torque available from the prime movers to the torque required to launch the vehicle, and controlling operation of the prime movers to launch the vehicle in response to the comparing step. The systemmore »« less
Full Text Available
Method of managing interference during delay recovery on a train system

Patent Gordon, Susanna P.; Evans, John A.

The present invention provides methods for preventing low train voltages and managing interference, thereby improving the efficiency, reliability, and passenger comfort associated with commuter trains. An algorithm implementing neural network technology is used to predict low voltages before they occur. Once voltages are predicted, then multiple trains can be controlled to prevent low voltage events. Further, algorithms for managing inference are presented in the present invention. Different types of interference problems are addressed in the present invention such as "Interference During Acceleration", "Interference Near Station Stops", and "Interference During Delay Recovery." Managing such interference avoids unnecessary brake/acceleration cycles during acceleration,more »« less
Full Text Available
Trip optimization system and method for a train

Patent Kumar, Ajith Kuttannair; Shaffer, Glenn Robert; Houpt, Paul Kenneth; ...

A system for operating a train having one or more locomotive consists with each locomotive consist comprising one or more locomotives, the system including a locator element to determine a location of the train, a track characterization element to provide information about a track, a sensor for measuring an operating condition of the locomotive consist, a processor operable to receive information from the locator element, the track characterizing element, and the sensor, and an algorithm embodied within the processor having access to the information to create a trip plan that optimizes performance of the locomotive consist in accordance with onemore »« less
Full Text Available
Method and system for training a visual prosthesis

Patent Fink, Wolfgang; Tarbell, Mark A.

A method for training a visual prosthesis includes presenting a non-visual reference stimulus corresponding to a reference image to a visual prosthesis patient. Training data sets are generated by presenting a series of stimulation patterns to the patient through the visual prosthesis. Each stimulation pattern in the series is determined at least in part on a received user perception input and a fitness function optimization algorithm. The presented stimulation patterns and the user perception inputs are stored and presented to a neural network off-line to determine a vision solution.
Full Text Available

Similar Records

Title: Adaptive model training system and method

Abstract

Citation Formats

Generating an Interpretable Family of Fuzzy Partitions From Data journal, June 2004

Real-time sensor validation for propulsion systems conference, February 2013

A turbine engine real-time test data validation and analysis system, generation 1.0 conference, February 2013

Generating an Interpretable Family of Fuzzy Partitions From Data
journal, June 2004

Real-time sensor validation for propulsion systems
conference, February 2013

A turbine engine real-time test data validation and analysis system, generation 1.0
conference, February 2013