Neural network based system for equipment surveillance
Abstract
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 the industrial process. 33 figs.
- Inventors:
- Issue Date:
- Research Org.:
- Univ. of Chicago, IL (United States)
- Sponsoring Org.:
- USDOE, Washington, DC (United States)
- OSTI Identifier:
- 644423
- Patent Number(s):
- 5745382
- Application Number:
- PAN: 8-521,892
- Assignee:
- ARCH Development Corp., Chicago, IL (United States)
- DOE Contract Number:
- W-31109-ENG-38
- Resource Type:
- Patent
- Resource Relation:
- Other Information: PBD: 28 Apr 1998
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; INSPECTION; EQUIPMENT; NEURAL NETWORKS; INDUSTRIAL PLANTS; TRAINING
Citation Formats
Vilim, R B, Gross, K C, and Wegerich, S W. Neural network based system for equipment surveillance. United States: N. p., 1998.
Web.
Vilim, R B, Gross, K C, & Wegerich, S W. Neural network based system for equipment surveillance. United States.
Vilim, R B, Gross, K C, and Wegerich, S W. Tue .
"Neural network based system for equipment surveillance". United States.
@article{osti_644423,
title = {Neural network based system for equipment surveillance},
author = {Vilim, R B and Gross, K C and Wegerich, S W},
abstractNote = {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 the industrial process. 33 figs.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Apr 28 00:00:00 EDT 1998},
month = {Tue Apr 28 00:00:00 EDT 1998}
}