Neural network based system for equipment surveillance

Title: Neural network based system for equipment surveillance

Full Record
Other Related Research

Abstract

A method and system for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process.

Inventors:

Vilim, Richard B. ^[1]; Gross, Kenneth C. ^[2]; Wegerich, Stephan W. ^[3]

(Aurora, IL)
(Bolingbrook, IL)
(Glendale Hts., IL)

Issue Date:: 1998-01-01

Research Org.:: Argonne National Laboratory (ANL), Argonne, IL

OSTI Identifier:: 871513

Patent Number(s):: 5745382

Assignee:: ARCH Development Corporation (Chicago, IL) ANL

DOE Contract Number:: W-31109-ENG-38

Resource Type:: Patent

Country of Publication:: United States

Language:: English

Subject:: neural; network; based; equipment; surveillance; method; performing; transient; signals; industrial; device; ascertain; operating; involves; steps; reading; memory; training; data; determining; weighting; values; achieving; target; outputs; close; output; inadequate; wavelet; parameters; determined; yield; desired; set; providing; characteristic; process; comparing; evaluate; process signals; neural network; industrial process; network based; training data; performing surveillance; desired set; neural net; transient signal; /706/702/

Citation Formats


                    Vilim, Richard B., Gross, Kenneth C., and Wegerich, Stephan W. Neural network based system for equipment surveillance.  United States: N. p., 1998. 
        Web.

Copy to clipboard


                    Vilim, Richard B., Gross, Kenneth C., & Wegerich, Stephan W. Neural network based system for equipment surveillance.  United States.

Copy to clipboard


                    Vilim, Richard B., Gross, Kenneth C., and Wegerich, Stephan W. Thu .  
        "Neural network based system for equipment surveillance".  United States.  https://www.osti.gov/servlets/purl/871513.

Copy to clipboard


                    
@article{osti_871513,

  title        = {Neural network based system for equipment surveillance},

  author       = {Vilim, Richard B. and Gross, Kenneth C. and Wegerich, Stephan W.},

  abstractNote = {A method and system for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of the industrial process.},

  doi          = {},

  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {1998},

  month        = {1}

}

Copy to clipboard

Patent:

View Patent

Save / Share:

Export Metadata

Save to My Library

Similar records in DOE Patents and OSTI.GOV collections:

Neural network based system for equipment surveillance

Patent Vilim, R.B.; Gross, K.C.; Wegerich, S.W.

A method and system are disclosed for performing surveillance of transient signals of an industrial device to ascertain the operating state. The method and system involves the steps of reading into a memory training data, determining neural network weighting values until achieving target outputs close to the neural network output. If the target outputs are inadequate, wavelet parameters are determined to yield neural network outputs close to the desired set of target outputs and then providing signals characteristic of an industrial process and comparing the neural network output to the industrial process signals to evaluate the operating state of themore » industrial process. 33 figs.« less
Neural network system and methods for analysis of organic materials and structures using spectral data

Patent Meyer, Bernd J. (Athens, GA); Sellers, Jeffrey P. (Suwanee, GA); Thomsen, Jan U. (Fredricksberg, DK)

Apparatus and processes for recognizing and identifying materials. Characteristic spectra are obtained for the materials via spectroscopy techniques including nuclear magnetic resonance spectroscopy, infrared absorption analysis, x-ray analysis, mass spectroscopy and gas chromatography. Desired portions of the spectra may be selected and then placed in proper form and format for presentation to a number of input layer neurons in an offline neural network. The network is first trained according to a predetermined training process; it may then be employed to identify particular materials. Such apparatus and processes are particularly useful for recognizing and identifying organic compounds such as complex carbohydrates,more »« less
Full Text Available
System and method for knowledge based matching of users in a network

Patent Verspoor, Cornelia Maria [Santa Fe, NM]; Sims, Benjamin Hayden [Los Alamos, NM]; Ambrosiano, John Joseph [Los Alamos, NM]; ...

A knowledge-based system and methods to matchmaking and social network extension are disclosed. The system is configured to allow users to specify knowledge profiles, which are collections of concepts that indicate a certain topic or area of interest selected from an. The system utilizes the knowledge model as the semantic space within which to compare similarities in user interests. The knowledge model is hierarchical so that indications of interest in specific concepts automatically imply interest in more general concept. Similarity measures between profiles may then be calculated based on suitable distance formulas within this space.
Full Text Available
NEBSESS. NEural Network Based System for Equipment Startup Surveillance

Technical Report Vilim, R.B.; Gross, K.C. [Argonne National Lab., IL (United States)]

NEBSESS is a system for equipment surveillance and fault detection which relies on a neural-network based means for diagnosing disturbances during startup and for automatically actuating the Sequential Probability Ratio Test (SPRT) as a signal validation means during steady-state operation.
Neural Network Based System for Equipment Startup Surveillance

Software Vilim, Richard B.; Gross, Kenny C.

NEBSESS is a system for equipment surveillance and fault detection which relies on a neural-network based means for diagnosing disturbances during startup and for automatically actuating the Sequential Probability Ratio Test (SPRT) as a signal validation means during steady-state operation.

Similar Records