Automated method for the systematic interpretation of resonance peaks in spectrum data

Damiano, Brian; Wood, Richard T

Title: Automated method for the systematic interpretation of resonance peaks in spectrum data

Abstract

A method for spectral signature interpretation. The method includes the creation of a mathematical model of a system or process. A neural network training set is then developed based upon the mathematical model. The neural network training set is developed by using the mathematical model to generate measurable phenomena of the system or process based upon model input parameter that correspond to the physical condition of the system or process. The neural network training set is then used to adjust internal parameters of a neural network. The physical condition of an actual system or process represented by the mathematical model is then monitored by extracting spectral features from measured spectra of the actual process or system. The spectral features are then input into said neural network to determine the physical condition of the system or process represented by the mathematical. More specifically, the neural network correlates the spectral features (i.e. measurable phenomena) of the actual process or system with the corresponding model input parameters. The model input parameters relate to specific components of the system or process, and, consequently, correspond to the physical condition of the process or system.

Inventors:

Damiano, Brian ^[1]; Wood, Richard T ^[1]

Knoxville, TN

Issue Date:: 1997-01-01

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

OSTI Identifier:: 870914

Patent Number(s):: 5623579

Assignee:: Martin Marietta Energy Systems, Inc. (Oak Ridge, TN)

Patent Classifications (CPCs):: Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y02 - TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE Y02E - REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y10 - TECHNICAL SUBJECTS COVERED BY FORMER USPC Y10S - TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS

Show more

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y02 - TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE Y02E - REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
Y02E30/30 - Nuclear fission reactors

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y10 - TECHNICAL SUBJECTS COVERED BY FORMER USPC Y10S - TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
Y10S706/915 - Power plant

G - PHYSICS G21 - NUCLEAR PHYSICS G21D - NUCLEAR POWER PLANT
G21D3/001 - {Computer implemented control}

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y02 - TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE Y02E - REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
Y02E30/00 - Energy generation of nuclear origin

G - PHYSICS G21 - NUCLEAR PHYSICS G21C - NUCLEAR REACTORS
G21C17/00 - Monitoring

G - PHYSICS G06 - COMPUTING G06K - RECOGNITION OF DATA
G06K9/00496 - {Recognising patterns in signals and combinations thereof

Show less

DOE Contract Number:: AC05-84OR21400

Resource Type:: Patent

Country of Publication:: United States

Language:: English

Subject:: automated; method; systematic; interpretation; resonance; peaks; spectrum; data; spectral; signature; creation; mathematical; model; process; neural; network; training; set; developed; based; generate; measurable; phenomena; input; parameter; correspond; physical; condition; adjust; internal; parameters; represented; monitored; extracting; features; measured; spectra; determine; specifically; correlates; corresponding; relate; specific; components; consequently; physical condition; automated method; spectral features; neural network; mathematical model; spectrum data; resonance peaks; neural net; resonance peak; spectral signature; process based; /706/376/

Citation Formats


                    Damiano, Brian, and Wood, Richard T. Automated method for the systematic interpretation of resonance peaks in spectrum data.  United States: N. p., 1997. 
        Web.

Copy to clipboard


                    Damiano, Brian, & Wood, Richard T. Automated method for the systematic interpretation of resonance peaks in spectrum data.  United States.

Copy to clipboard


                    Damiano, Brian, and Wood, Richard T. Wed .  
        "Automated method for the systematic interpretation of resonance peaks in spectrum data".  United States.  https://www.osti.gov/servlets/purl/870914.

Copy to clipboard


                    
@article{osti_870914,

  title        = {Automated method for the systematic interpretation of resonance peaks in spectrum data},

  author       = {Damiano, Brian and Wood, Richard T},

  abstractNote = {A method for spectral signature interpretation. The method includes the creation of a mathematical model of a system or process. A neural network training set is then developed based upon the mathematical model. The neural network training set is developed by using the mathematical model to generate measurable phenomena of the system or process based upon model input parameter that correspond to the physical condition of the system or process. The neural network training set is then used to adjust internal parameters of a neural network. The physical condition of an actual system or process represented by the mathematical model is then monitored by extracting spectral features from measured spectra of the actual process or system. The spectral features are then input into said neural network to determine the physical condition of the system or process represented by the mathematical. More specifically, the neural network correlates the spectral features (i.e. measurable phenomena) of the actual process or system with the corresponding model input parameters. The model input parameters relate to specific components of the system or process, and, consequently, correspond to the physical condition of the process or system.},

  doi          = {},

  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {1997},

  month        = {1}

}

Copy to clipboard

Patent:

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Statistical algorithm for automated signature analysis of power spectral density data
journal, January 1977

Piety, K. R.
Progress in Nuclear Energy, Vol. 1, Issue 2-4
https://doi.org/10.1016/0149-1970(77)90127-5

An introduction to computing with neural nets
journal, January 1987

Lippmann, R.
IEEE ASSP Magazine, Vol. 4, Issue 2
https://doi.org/10.1109/MASSP.1987.1165576

30 years of adaptive neural networks: perceptron, Madaline, and backpropagation
journal, January 1990

Widrow, B.; Lehr, M. A.
Proceedings of the IEEE, Vol. 78, Issue 9
https://doi.org/10.1109/5.58323

A neural network methodology for process fault diagnosis
journal, December 1989

Venkatasubramanian, Venkat; Chan, King
AIChE Journal, Vol. 35, Issue 12
https://doi.org/10.1002/aic.690351210

Long-term automated surveillance of a commercial nuclear power plant
journal, January 1985

Smith, C. M.; Gonzalez, R. C.
Progress in Nuclear Energy, Vol. 15
https://doi.org/10.1016/0149-1970(85)90018-6

Similar Records in DOE Patents and OSTI.GOV collections:

Automated method for the systematic interpretation of resonance peaks in spectrum data

Patent Damiano, B; Wood, R T

A method is described for spectral signature interpretation. The method includes the creation of a mathematical model of a system or process. A neural network training set is then developed based upon the mathematical model. The neural network training set is developed by using the mathematical model to generate measurable phenomena of the system or process based upon model input parameter that correspond to the physical condition of the system or process. The neural network training set is then used to adjust internal parameters of a neural network. The physical condition of an actual system or process represented by themore » « less
Method and apparatus for current-output peak detection

Patent De Geronimo, Gianluigi

A method and apparatus for a current-output peak detector. A current-output peak detector circuit is disclosed and works in two phases. The peak detector circuit includes switches to switch the peak detector circuit from the first phase to the second phase upon detection of the peak voltage of an input voltage signal. The peak detector generates a current output with a high degree of accuracy in the second phase.
Full Text Available
Control method for peak power delivery with limited DC-bus voltage

Patent Edwards, John; Xu, Longya; Bhargava, Brij B.

A method for driving a neutral point-clamped multi-level voltage source inverter supplying a synchronous motor is provided. A DC current is received at a neutral point-clamped multi-level voltage source inverter. The inverter has first, second, and third output nodes. The inverter also has a plurality of switches. A desired speed of a synchronous motor connected to the inverter by the first second and third nodes is received by the inverter. The synchronous motor has a rotor and the speed of the motor is defined by the rotational rate of the rotor. A position of the rotor is sensed, current flowingmore » « less
Full Text Available
Method and apparatus for reducing rotor blade deflections, loads, and/or peak rotational speed

Patent Moroz, Emilian Mieczyslaw; Pierce, Kirk Gee

A method for reducing at least one of loads, deflections of rotor blades, or peak rotational speed of a wind turbine includes storing recent historical pitch related data, wind related data, or both. The stored recent historical data is analyzed to determine at least one of whether rapid pitching is occurring or whether wind speed decreases are occurring. A minimum pitch, a pitch rate limit, or both are imposed on pitch angle controls of the rotor blades conditioned upon results of the analysis.
Full Text Available
Load controller and method to enhance effective capacity of a photovoltaic power supply using a dynamically determined expected peak loading

Patent Perez, Richard

A load controller and method are provided for maximizing effective capacity of a non-controllable, renewable power supply coupled to a variable electrical load also coupled to a conventional power grid. Effective capacity is enhanced by monitoring power output of the renewable supply and loading, and comparing the loading against the power output and a load adjustment threshold determined from an expected peak loading. A value for a load adjustment parameter is calculated by subtracting the renewable supply output and the load adjustment parameter from the current load. This value is then employed to control the variable load in an amountmore » « less
Full Text Available

Similar Records

Title: Automated method for the systematic interpretation of resonance peaks in spectrum data

Abstract

Citation Formats

Statistical algorithm for automated signature analysis of power spectral density data journal, January 1977

An introduction to computing with neural nets journal, January 1987

30 years of adaptive neural networks: perceptron, Madaline, and backpropagation journal, January 1990

A neural network methodology for process fault diagnosis journal, December 1989

Long-term automated surveillance of a commercial nuclear power plant journal, January 1985

Statistical algorithm for automated signature analysis of power spectral density data
journal, January 1977

An introduction to computing with neural nets
journal, January 1987

30 years of adaptive neural networks: perceptron, Madaline, and backpropagation
journal, January 1990

A neural network methodology for process fault diagnosis
journal, December 1989

Long-term automated surveillance of a commercial nuclear power plant
journal, January 1985